Search results

Title: Modeling physical causality of action verbs for grounded language understanding
Creator: Gao, Qiaozi
Date: 2019
Collection: Electronic Theses & Dissertations
Description: Building systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other's intention, to connect language with concepts in the...
Show moreBuilding systems that can understand and communicate through human natural language is one of the ultimate goals in AI. Decades of natural language processing research has been mainly focused on learning from large amounts of language corpora. However, human communication relies on a significant amount of unverbalized information, which is often referred as commonsense knowledge. This type of knowledge allows us to understand each other's intention, to connect language with concepts in the world, and to make inference based on what we hear or read. Commonsense knowledge is generally shared among cognitive capable individuals, thus it is rarely stated in human language. This makes it very difficult for artificial agents to acquire commonsense knowledge from language corpora. To address this problem, this dissertation investigates the acquisition of commonsense knowledge, especially knowledge related to basic actions upon the physical world and how that influences language processing and grounding.Linguistics studies have shown that action verbs often denote some change of state (CoS) as the result of an action. For example, the result of "slice a pizza" is that the state of the object (pizza) changes from one big piece to several smaller pieces. However, the causality of action verbs and its potential connection with the physical world has not been systematically explored. Artificial agents often do not have this kind of basic commonsense causality knowledge, which makes it difficult for these agents to work with humans and to reason, learn, and perform actions.To address this problem, this dissertation models dimensions of physical causality associated with common action verbs. Based on such modeling, several approaches are developed to incorporate causality knowledge to language grounding, visual causality reasoning, and commonsense story comprehension.
Show less

Title: Constraining nuclear weak interactions in astrophysics and new many-core algorithms for neuroevolution
Creator: Sullivan, Christopher James
Date: 2018
Collection: Electronic Theses & Dissertations
Description: "Weak interactions involving atomic nuclei are critical components in a broad range of astrophysical phenomenon. As allowed Gamow-Teller transitions are the primary path through which weak interactions in nuclei operate in astrophysical contexts, the constraint of these nuclear transitions is an important goal of nuclear astrophysics. In this work, the charged current nuclear weak interaction known as electron capture is studied in the context of stellar core-collapse supernovae (CCSNe)....
Show more"Weak interactions involving atomic nuclei are critical components in a broad range of astrophysical phenomenon. As allowed Gamow-Teller transitions are the primary path through which weak interactions in nuclei operate in astrophysical contexts, the constraint of these nuclear transitions is an important goal of nuclear astrophysics. In this work, the charged current nuclear weak interaction known as electron capture is studied in the context of stellar core-collapse supernovae (CCSNe). Specifically, the sensitivity of the core-collapse and early post-bounce phases of CCSNe to nuclear electron capture rates are examined. Electron capture rates are adjusted by factors consistent with uncertainties indicated by comparing theoretical rates to those deduced from charge-exchange and beta-decay measurements. With the aide of such sensitivity studies, the diverse role of electron capture on thousands of nuclear species is constrained to a few tens of nuclei near N 503030 and A 803030 which dictate the primary response of CCSNe to nuclear electron capture. As electron capture is shown to be a leading order uncertainty during the core-collapse phase of CCSNe, future experimental and theoretical efforts should seek to constrain the rates of nuclei in this region. Furthermore, neutral current neutrino-nuclear interactions in the tens-of-MeV energy range are important in a variety of astrophysical environments including core-collapse supernovae as well as in the synthesis of some of the solar systems rarest elements. Estimates for inelastic neutrino scattering on nuclei are also important for neutrino detector construction aimed at the detection of astrophysical neutrinos. Due to the small cross sections involved, direct measurements are rare and have only been performed on a few nuclei. For this reason, indirect measurements provide a unique opportunity to constrain the nuclear transition strength needed to infer inelastic neutrino-nucleus cross sections. Herein the (6Li, 6Li0 ) inelastic scattering reaction at 100 MeV/u is shown to indirectly select the relevant transitions for inelastic neutrino-nucleus scattering. Specifically, the probes unique selectivity of isovector-spin transfer excitations (delta-S = 1, delta-T = 1, delta-Tz = 0) is demonstrated, thereby allowing the extraction of Gamow-Teller transition strength in the inelastic channel. Finally, the development and performance of a newly established technique for the subfield of artificial intelligence known as neuroevolution is described. While separate from the physics that is discussed, these algorithmic advancements seek to improve the adoption of machine learning in the scientific domain by enabling neuroevolution to take advantage of modern heterogeneous compute architectures. Because the evolution of neural network populations offloads the choice of specific details about the neural networks to an evolutionary search algorithm, neuroevolution can increase the accessibility of machine learning. However, the evolution of neural networks through parameter and structural space presents a novel divergence problem when mapping the evaluation of these networks to many-core architectures. The principal focus of the algorithm optimizations described herein are on improving the feed-forward evaluation time when tens-to-hundreds of thousands of heterogeneous neural networks are evaluated concurrently."--Pages ii-iii.
Show less

Title: IPCA : an intelligent control architecture based on the generic task approach to knowledge-based systems
Creator: Decker, David Bruce
Date: 1995
Collection: Electronic Theses & Dissertations

Title: Decision biases in user agreement with intelligent decision aids
Creator: Solomon, Jacob Bennion
Date: 2015
Collection: Electronic Theses & Dissertations
Description: Intelligent Decision Aids (IDAs) are emerging technologies used in areas such as medicine, finance, and e-commerce that leverage artificial intelligence, data mining, or related computational methods to provide recommendations to decision makers. An important goal for designers should be to help users identify and accept good recommendations and ignore poor recommendations. However, considerable research has found that IDA users frequently make poor decisions about which recommendations to...
Show moreIntelligent Decision Aids (IDAs) are emerging technologies used in areas such as medicine, finance, and e-commerce that leverage artificial intelligence, data mining, or related computational methods to provide recommendations to decision makers. An important goal for designers should be to help users identify and accept good recommendations and ignore poor recommendations. However, considerable research has found that IDA users frequently make poor decisions about which recommendations to follow.I present findings from three studies that provide evidence of four distinct decision-making biases related to IDA-supported decision making. These biases are characterized by an increase in users' agreement with an IDA's recommendations that is unassociated with the recommendations themselves but associated with some other aspect of the design of the IDA or of the user.In an experiment that manipulated the perceived customizability of an IDA that assisted users in predicting the outcomes of baseball games, I found that users who believed they had customized the IDA were more likely to follow both good and poor recommendations than other users who received identical recommendations from the IDA but did not customize its logic. This finding is evidence of a customization bias. Importantly, this study found that customization bias is not caused by users believing they have improved the algorithm by customizing it.In a second experiment, subjects were encouraged to believe that the system had either high or low efficacy prior to seeing recommendations. This encouragement created an expectations bias in which subjects were more likely to follow both good and poor recommendations when they had higher expectations of the IDA's efficacy than other subjects who had expected the IDA's algorithm to perform poorly. In the third experiment, I assessed decision making by users of an IDA for recommending exercise activities. Subjects who used a customizable version of this IDA, where the recommendations depended on how users configured the IDA, were more likely to agree with the recommendations than users who received recommendations of similar quality but did not customize the IDA. This finding shows additional evidence of customization bias, demonstrating that it extends to IDAs where the customizability has real influence over the recommendations rather than merely perceived customization as in the first study. In this study I also found that when users believe that an IDA's internal logic is more clear and understandable, they are more likely to follow recommendations regardless of their quality. This finding suggests a transparency bias. There was a strong relationship between the quality of recommendations that subjects received and the quality of their decisions, indicating that when decision makers are supported by IDAs, the quality of recommendations is important to system success. However, subjects who performed the decision task unaided by an IDA performed as well as the IDA-supported subjects. These findings show that when decision makers are aided by an IDA, the system affects the decision making process by requiring users to evaluate recommendations. IDA users may make biased evaluations due to characteristics of the interface and interaction design of the system as well as individual characteristics of the users. In the concluding chapter I discuss the implications of these findings for the design of IDAs and related socio-technical systems, as well as for future work on computer-supported decision making.
Show less

Title: Optimality and hierarchical representation in emergent neural Turing machines and their visual navigation
Creator: Zheng, Zejia
Date: 2018
Collection: Electronic Theses & Dissertations
Description: "Traditional Turing Machines (TMs) are symbolic in the sense that representations in these TMs are static and hand-crafted. This paper presents a new kind of TM - emergent neural Turing Machine. By neural, we mean that the control of the TM has neurons as basic computing elements. By emergent, we mean that the internal representations are formed during learning without hand-crafting. Developmental Network-1 (DN-1) uses emergent representation to perform Turing Computation but the internal...
Show more"Traditional Turing Machines (TMs) are symbolic in the sense that representations in these TMs are static and hand-crafted. This paper presents a new kind of TM - emergent neural Turing Machine. By neural, we mean that the control of the TM has neurons as basic computing elements. By emergent, we mean that the internal representations are formed during learning without hand-crafting. Developmental Network-1 (DN-1) uses emergent representation to perform Turing Computation but the internal hierarchy is handcrafted with emergent features. The major novelty of the proposed TM (Developmental Network-2) over DN-1 is that the representational hierarchy inside DN-2 is emergent and fluid. DN-2 grows complex hierarchies by dynamically allowing initialization of neurons with different domains of connection. Its optimality in terms of maximum likelihood properties is established under the conditions of limited learning experience and resources. Although DN-2 is meant for general learning tasks, we experimented with a complex task-- vision-guided navigation in simulated and natural worlds using DN-2. Real-world and simulated navigation experiments showed that DN-2 successfully learned rules of navigation with image and other inputs. The formed hierarchical representation in DN-2 focuses on important navigation features like road edges while disregarding the distractors like shadows edges."--Page ii.
Show less

Title: Developmental learning with applications to attention, task transfer and user presence detection
Creator: Huang, Xiao
Date: 2005
Collection: Electronic Theses & Dissertations

Title: On the application of relevance measures in mechanical deduction
Creator: Soddy, James Stephen
Date: 1982
Collection: Electronic Theses & Dissertations

Title: Representation and processes of pedagogic knowledge
Creator: Grossman, Harold Charles
Date: 1978
Collection: Electronic Theses & Dissertations

Title: CMOS VLSI implementations of a new feedback neural network architecture
Creator: Wang, Yiwen
Date: 1991
Collection: Electronic Theses & Dissertations

Title: Cortex-inspired developmental learning for vision-based navigation, attention and recognition
Creator: Ji, Zhengping
Date: 2009
Collection: Electronic Theses & Dissertations

Title: Searle's Chinese box : the Chinese room argument and artificial intelligence
Creator: Hauser, Larry Steven
Date: 1993
Collection: Electronic Theses & Dissertations

Title: Grounded language processing for action understanding and justification
Creator: Yang, Shaohua (Graduate of Michigan State University)
Date: 2019
Collection: Electronic Theses & Dissertations
Description: Recent years have witnessed an increasing interest on cognitive robots entering into our life. In order to reason, collaborate and communicate with human in the shared physical world, the agents need to understand the meaning of human language, especially the actions, and connect them to the physical world. Furthermore, to make the communication more transparent and trustworthy, the agents should have human-like action justification ability to explain their decision-making behaviors. The goal...
Show moreRecent years have witnessed an increasing interest on cognitive robots entering into our life. In order to reason, collaborate and communicate with human in the shared physical world, the agents need to understand the meaning of human language, especially the actions, and connect them to the physical world. Furthermore, to make the communication more transparent and trustworthy, the agents should have human-like action justification ability to explain their decision-making behaviors. The goal of this dissertation is to develop approaches that learns to understand actions in the perceived world through language communication. Towards this goal, we study three related problems. Semantic role labeling captures semantic roles (or participants) such as agent, patient and theme associated with verbs from text. While it provides important intermediate semantic representations for many traditional NLP tasks, it does not capture grounded semantics with which an artificial agent can reason, learn, and perform the actions. We utilize semantic role labeling to connect the visual semantics with linguistic semantics. On one hand, this structured semantic representation can help extend the traditional visual scene understanding instead of simply object recognition and relation detection, which is important for achieving human robot collaboration tasks. On the other hand, due to the shared common ground, not every language instruction is fully specified explicitly. We proposed to not only ground explicit semantic roles, but also implicit roles which is hidden during the communication. Our empirical results have shown that by incorporate the semantic information, we achieve better grounding performance, and also a better semantic representation of the visual world. Another challenge for an agent is to explain to human why it recognizes what's going on as a certain action. With the recent advance of deep learning, A lot of works have shown to be very effective on action recognition. But most of them function like black-box models and have no interpretations of the decisions which are given. To enable collaboration and communication between humans and agents, we developed a generative conditional variational autoencoder (CVAE) approach which allows the agent to learn to acquire commonsense evidence for action justification. Our empirical results have shown that, compared to a typical attention-based model, CVAE has a significantly higher explanation ability in terms of identifying correct commonsense evidence to justify perceived actions. The experiment on communication grounding further shows that the commonsense evidence identified by CVAE can be communicated to humans to achieve a significantly higher common ground between humans and agents. The third problem combines the action grounding with action justification in the context of visual commonsense reasoning. Humans have tremendous visual commonsense knowledge to answer the question and justify the rationale, but the agent does not. On one hand, this process requires the agent to jointly ground both the answers and rationales to the images. On the other hand, it also requires the agent to learn the relation between the answer and the rationale. We propose a deep factorized model to have a better understanding of the relations between the image, question, answer and rationale. Our empirical results have shown that the proposed model outperforms strong baselines in the overall performance. By explicitly modeling factors of language grounding and commonsense reasoning, the proposed model provides a better understanding of effects of these factors on grounded action justification.
Show less

Title: Nonparametric procedures for learning with an imperfect teacher
Creator: Richter, Ronald Joseph, 1945-
Date: 1972
Collection: Electronic Theses & Dissertations

Title: Cortex-inspired goal-directed recurrent networks for developmental visual attention and recognition with complex backgrounds
Creator: Luciw, Matthew
Date: 2010
Collection: Electronic Theses & Dissertations

Title: Interactive learning of verb semantics towards human-robot communication
Creator: She, Lanbo
Date: 2017
Collection: Electronic Theses & Dissertations
Description: "In recent years, a new generation of cognitive robots start to enter our lives. Robots such like ASIMO, PR2, and Baxter have been studied and applied in education and service applications. Different from traditional industry robots doing specific repetitive tasks in a well controlled environment, cognitive robots must be able to work with human partners in a dynamic environment which is filled with uncertainties and exceptions. It is unlikely to pre-program every type of knowledge (e.g.,...
Show more"In recent years, a new generation of cognitive robots start to enter our lives. Robots such like ASIMO, PR2, and Baxter have been studied and applied in education and service applications. Different from traditional industry robots doing specific repetitive tasks in a well controlled environment, cognitive robots must be able to work with human partners in a dynamic environment which is filled with uncertainties and exceptions. It is unlikely to pre-program every type of knowledge (e.g., perceptual knowledge like different colors or shapes; action knowledge like how to complete a task) into the robot systems ahead of time. Just like how children learn from their parents, it's desirable for robots to continuously acquire knowledge and learn from human partners on how to handle novel and unknown situations. Driven by this motivation, the goal of this dissertation is to develop approaches that allow robots to acquire and refine knowledge, particularly, knowledge related to verbs and actions, through interaction/dialogue with its human partner. Towards this goal, this dissertation has made following contributions i . As a first step, we propose a goal state based verb semantics and develop a three-tier action/task knowledge representation. This representation on one hand supports the connection between symbolic representations of language and continuous sensori-motor representations of the robots; and on the other hand, supports the application of existing planning algorithms to address novel situations. Our empirical results have shown that, given this representation, the robot can immediately apply the newly learned action knowledge to perform actions under novel situations. Secondly, the goal state representation and the three-tier structure are integrated into a dialogue system on board of a SCHUNK robotic arm to learn new actions through human-robot dialogue in a simplified blocks world. For a novel complex action, the human can give an illustration through dialogue using robot's existing action knowledge. Comparing the environment changes before and after the action illustration, the robot can identify a goal state to represent the novel action, which can be immediately applied to new environments. Empirical studies have shown that action knowledge can be acquired by following human instructions. Furthermore, the results also demonstrate that step-by-step instructions lead to better learning performance compared to one-shot instructions. To solve the insufficiency issue of applying the single goal state representation in more complex domains (e.g., kitchen and living room), the single goal state is extended to a hierarchical hypothesis space to capture different possible outcomes of a verb action. Our empirical results demonstrate that the representation of hypothesis space, combined with the learned hypothesis selection algorithm, outperforms approaches using single hypothesis representation. Lastly, we address uncertainties in the environment for verb acquisition. Previous works rely on perfect environment sensing and human language understanding, which does not hold in real world situation. In addition, rich interactions between teachers and learners as observed in human teaching/learning have not been explored. To address these limitations, the last part presents a new interactive learning approach that allows robots to proactively engage in interaction with human partners by asking good questions to handle uncertainties of the environment. Reinforcement learning is applied for the robot to acquire an optimal policy for its question-asking behaviors by maximizing the long-term reward. Empirical results have shown that the interactive learning approach leads to more reliable models for grounded verb semantics, especially in the noisy environments."--Pages ii-iii.
Show less

Title: Towards Robust and Secure Face Recognition : Defense Against Physical and Digital Attacks
Creator: Deb, Debayan
Date: 2021
Collection: Electronic Theses & Dissertations
Description: The accuracy, usability, and touchless acquisition of state-of-the-art automated face recognition systems (AFR) have led to their ubiquitous adoption in a plethora of domains, including mobile phone unlock, access control systems, and payment services. Despite impressive recognition performance, prevailing AFR systems remain vulnerable to the growing threat of face attacks which can be launched in both physical and digital domains. Face attacks can be broadly classified into three attack...
Show moreThe accuracy, usability, and touchless acquisition of state-of-the-art automated face recognition systems (AFR) have led to their ubiquitous adoption in a plethora of domains, including mobile phone unlock, access control systems, and payment services. Despite impressive recognition performance, prevailing AFR systems remain vulnerable to the growing threat of face attacks which can be launched in both physical and digital domains. Face attacks can be broadly classified into three attack categories: (i) Spoof attacks: artifacts in the physical domain (e.g., 3D masks, eye glasses, replaying videos), (ii) Adversarial attacks: imperceptible noises added to probes for evading AFR systems, and (iii) Digital manipulation attacks: entirely or partially modified photo-realistic faces using generative models. Each of these categories is composed of different attack types. For example, each spoof medium, e.g., 3D mask and makeup, constitutes one attack type. Likewise, in adversarial and digital manipulation attacks, each attack model, designed by unique objectives and losses, may be considered as one attack type. Thus, the attack categories and types form a 2-layer tree structure encompassing the diverse attacks. Such a tree will inevitably grow in the future. Given the growing dissemination of ``fake news” and "deepfakes", the research community and social media platforms alike are pushing towards generalizable defense against continuously evolving and sophisticated face attacks. In this dissertation, we first propose a set of defense methods that achieve state-of-the-art performance in detecting attack types within individual attack categories, both physical (e.g., face spoofs) and digital (e.g., adversarial faces and digital manipulation), then introduce a method for simultaneously safeguarding against each attack.First, in an effort to impart generalizability and interpretability to face spoof detection systems, we propose a new face anti-spoofing framework specifically designed to detect unknown spoof types, namely, Self-Supervised Regional Fully Convolutional Network (SSR-FCN), that is trained to learn local discriminative cues from a face image in a self-supervised manner. The proposed framework improves generalizability while maintaining the computational efficiency of holistic face anti-spoofing approaches (< 4 ms on a Nvidia GTX 1080Ti GPU). The proposed method is also interpretable since it localizes which parts of the face are labeled as spoofs. Experimental results show that SSR-FCN can achieve True Detection Rate (TDR) = 65% @ 2.0% False Detection Rate (FDR) when evaluated on a dataset comprising of 13 different spoof types under unknown attacks while achieving competitive performances under standard benchmark face anti-spoofing datasets (Oulu-NPU, CASIA-MFSD, and Replay-Attack).Next, we address the problem of defending against adversarial attacks. We first propose, AdvFaces, an automated adversarial face synthesis method that learns to generate minimal perturbations in the salient facial regions. Once AdvFaces is trained, it can automatically evade state-of-the-art face matchers with attack success rates as high as 97.22% and 24.30% at 0.1% FAR for obfuscation and impersonation attacks, respectively. We then propose a new self-supervised adversarial defense framework, namely FaceGuard, that can automatically detect, localize, and purify a wide variety of adversarial faces without utilizing pre-computed adversarial training samples. FaceGuard automatically synthesizes diverse adversarial faces, enabling a classifier to learn to distinguish them from bona fide faces. Concurrently, a purifier attempts to remove the adversarial perturbations in the image space. FaceGuard can achieve 99.81%, 98.73%, and 99.35% detection accuracies on LFW, CelebA, and FFHQ, respectively, on six unseen adversarial attack types.Finally, we take the first steps towards safeguarding AFR systems against face attacks in both physical and digital domains. We propose a new unified face attack detection framework, namely UniFAD, which automatically clusters similar attacks and employs a multi-task learning framework to learn salient features to distinguish between bona fides and coherent attack types. The proposed UniFAD can detect face attacks from 25 attack types across all 3 attack categories with TDR = 94.73% @ 0.2% FDR on a large fake face dataset, namely GrandFake. Further, UniFAD can identify whether attacks are adversarial, digitally manipulated, or contain spoof artifacts, with 97.37% classification accuracy.
Show less

Title: Adaptive and Automated Deep Recommender Systems
Creator: Zhao, Xiangyu
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Recommender systems are intelligent information retrieval applications, and have been leveraged in numerous domains such as e-commerce, movies, music, books, and point-of-interests. They play a crucial role in the users' information-seeking process, and overcome the information overload issue by recommending personalized items (products, services, or information) that best match users' needs and preferences. Driven by the recent advances in machine learning theories and the prevalence of deep...
Show moreRecommender systems are intelligent information retrieval applications, and have been leveraged in numerous domains such as e-commerce, movies, music, books, and point-of-interests. They play a crucial role in the users' information-seeking process, and overcome the information overload issue by recommending personalized items (products, services, or information) that best match users' needs and preferences. Driven by the recent advances in machine learning theories and the prevalence of deep learning techniques, there have been tremendous interests in developing deep learning based recommender systems. They have unprecedentedly advanced effectiveness of mining the non-linear user-item relationships and learning the feature representations from massive datasets, which produce great vitality and improvements in recommendations from both academic and industry communities.Despite above prominence of existing deep recommender systems, their adaptiveness and automation still remain under-explored. Thus, in this dissertation, we study the problem of adaptive and automated deep recommender systems. Specifically, we present our efforts devoted to building adaptive deep recommender systems to continuously update recommendation strategies according to the dynamic nature of user preference, which maximizes the cumulative reward from users in the practical streaming recommendation scenarios. In addition, we propose a group of automated and systematic approaches that design deep recommender system frameworks effectively and efficiently from a data-driven manner. More importantly, we apply our proposed models into a variety of real-world recommendation platforms and have achieved promising enhancements of social and economic benefits.
Show less

Title: Optimizing for Mental Representations in the Evolution of Artificial Cognitive Systems
Creator: Kirkpatrick, Douglas Andrew
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Mental representations, or sensor-independent internal models of the environment, are used to interpret the world and make decisions based upon that understanding. For example, a human sees dark clouds in the sky, recalls that often dark clouds mean rain (a mental representation), and consequently decides to wear a raincoat. I seek to identify, understand, and encourage the evolution of these representations in silico. Previous work identified an information-theoretic tool, referred to as R,...
Show moreMental representations, or sensor-independent internal models of the environment, are used to interpret the world and make decisions based upon that understanding. For example, a human sees dark clouds in the sky, recalls that often dark clouds mean rain (a mental representation), and consequently decides to wear a raincoat. I seek to identify, understand, and encourage the evolution of these representations in silico. Previous work identified an information-theoretic tool, referred to as R, that measures mental representations in artificial cognitive systems (e.g., Markov Brains or Recurrent Neural Networks). Further work found that selecting for R, along with task performance, in the evolution of artificial cognitive systems leads to better overall performance on a given task. Here I explore the implications and opportunities of this modified selection process, referred to as R-augmentation. After an overview of common methods, techniques, and computational substrates in Chapter 1, a series of working chapters experimentally demonstrate the capabilities and possibilities of R-augmentation. First, in Chapter 2, I address concerns regarding potential limitations of R-augmentation. This includes an refutation of suspected negative impacts on the system’s ability to generalize within-domain and the system’s robustness to sensor noise. To the contrary, the systems evolved with R-augmentation tend to perform better than those evolved without, in the context of noisy environments and different computational components. In Chapter 3 I examine how R-augmentation works across different cognitive structures, focusing on the evolution of genetic programming related structures and the effect that augmentation has on the distribution of their representations. For Chapter 4, in the context of the all-component Markov Brain (referred to as a Buffet Brain, see [Hintze et al., 2019]) I analyze potential reasons that explain why R-augmentation works; the mechanism seems to be based on evolutionary dynamics as opposed to structural or component differences. Next, I demonstrate a novel usage of R-augmentation in Chapter 5; with R-augmentation, one can use far fewer training examples during evolution and the resulting systems still perform approximately as well as those that were trained on the full set of examples. This advantage in increased performance at low sample size is found in some examples of in-domain and out-domain generalization, with the ”worst-case” scenario being that the networks created by R-augmentation perform as well as their unaugmented equivalents. Lastly, in Chapter 6 I move beyond R-augmentation to explore using other neuro-correlates - particularly the distribution of representations, called smearedness - as part of the fitness function. I investigate the possibility of using MAP-Elites to identify an optimal value of smearedness for augmentation or for use as an optimization method in its own right. Taken together, these investigations demonstrate both the capabilities and limitations of R-augmentation, and open up pathways for future research.
Show less

Title: The Evolutionary Origins of Cognition : Understanding the early evolution of biological control systems and general intelligence
Creator: Carvalho Pontes, Anselmo
Date: 2021
Collection: Electronic Theses & Dissertations
Description: In the last century, we have made great strides towards understanding natural cognition and recreating it artificially. However, most cognitive research is still guided by an inadequate theoretical framework that equates cognition to a computer system executing a data processing task. Cognition, whether natural or artificial, is not a data processing system; it is a control system.At cognition's core is a value system that allows it to evaluate current conditions and decide among two or more...
Show moreIn the last century, we have made great strides towards understanding natural cognition and recreating it artificially. However, most cognitive research is still guided by an inadequate theoretical framework that equates cognition to a computer system executing a data processing task. Cognition, whether natural or artificial, is not a data processing system; it is a control system.At cognition's core is a value system that allows it to evaluate current conditions and decide among two or more courses of action. Memory, learning, planning, and deliberation, rather than being essential cognitive abilities, are features that evolved over time to support the primary task of deciding “what to do next”. I used digital evolution to recreate the early stages in the evolution of natural cognition, including the ability to learn. Interestingly, I found cognition evolves in a predictable manner, with more complex abilities evolving in stages, by building upon previous simpler ones. I initially investigated the evolution of dynamic foraging behaviors among the first animals known to have a central nervous system, Ediacaran microbial mat miners. I then followed this up by evolving more complex forms of learning. I soon encountered practical limitations of the current methods, including exponential demand of computational resources and genetic representations that were not conducive to further scaling. This type of complexity barrier has been a recurrent issue in digital evolution. Nature, however, is not limited in the same ways; through evolution, it has created a language to express robust, modular, and flexible control systems of arbitrary complexity and apparently open-ended evolvability. The essential features of this language can be captured in a digital evolution platform. As an early demonstration of this, I evolved biologically plausible regulatory systems for virtual cyanobacteria. These systems regulate the cells' growth, photosynthesis and replication given the daily light cycle, the cell's energy reserves, and levels of stress. Although simple, this experimental system displays dynamics and decision-making mechanisms akin to biology, with promising potential for open-ended evolution of cognition towards general intelligence.
Show less

Title: Towards Proprioceptive Grasping With Soft Robotic Hands
Creator: da Silva Pinto, Thassyo
Date: 2021
Collection: Electronic Theses & Dissertations
Description: Various robotic hands, gloves, and grippers have been developed for manufacturing, prosthetics, and rehabilitation. However, the use of rigid links and joints presents challenges in control and safe interactions with humans. The emerging field of soft robotics seeks to create machines that are soft, compliant, and capable of withstanding damage, wear and high stress. This dissertation is focused on advancing soft actuators, soft sensors, and perception for ultimately realizing proprioceptive...
Show moreVarious robotic hands, gloves, and grippers have been developed for manufacturing, prosthetics, and rehabilitation. However, the use of rigid links and joints presents challenges in control and safe interactions with humans. The emerging field of soft robotics seeks to create machines that are soft, compliant, and capable of withstanding damage, wear and high stress. This dissertation is focused on advancing soft actuators, soft sensors, and perception for ultimately realizing proprioceptive grasping with soft robotic hands.In this work, several types of soft pneumatic actuators (SPAs) have been tested, fabricated, and tested, including one embedded with 3D-printed conductive polylactic acid (CPLA) layer capable of stiffness tuning and shape modulation. A gripper made of two soft actuators has been prototyped to demonstrate grasping of objects of different sizes and shapes, with desired posture-holding capabilities. Carbon nanotube (CNT)-based flexible sensor arrays have been designed, fabricated, and integrated to SPAs to provide distributed strain measurements. The presented approach allows customized design of stretchable sensor arrays with varied size and shape. Simulation and experimentation have been performed in order to analyze the soft actuator deformation during bending, and to confirm the capability of the integrated sensor array for capturing the actuator deformation. 3D printing of touch and pressure sensors has been further investigated for potential use in robotic hands. In particular, a novel process has been introduced for producing soft conductors and pressure sensors, involving first 3D-printing microchannels in soft substrates and then filling the channel with liquid metal. With a PolyJet printer, functional straight microchannels have been fabricated with sizes down to 150 x 150 micrometers in the cross-section area. In addition, spiral-shaped pressure sensors have been developed with a cross-section size of 350 x 350 micrometers and overall thickness of 1.5 mm (50A and 70A Shore Hardness). Although the sensors require a relatively large pressure threshold to operate, they have shown the ability to withstand high pressures up to 1 MPa and thus have potential to be used in industrial applications among others. Finally, preliminary computational exploration of intelligent grasping has been performed. In particular, the classification of soft grasped objects has been examined through a neuroevolution process for artificial brains. Simulation with SOFA (Simulation Open Framework Architecture) has been conducted to produce the emulated contact force measurements, which have been used to train artificial neural networks, including Markov Brains from the Modular Agent-Based Evolver (MABE) platform, to properly classify the shape and stiffness of the grasped objects.
Show less

MSU Libraries

Digital Repository

Enabled Filters

Pages

Pages

MSU Libraries

Digital Repository

You are here

Search results

Pages

Pages