检索结果-内蒙古大学图书馆

作者： IAN GEMP University of Massachusetts Amherst

学位级别：博士

Many existing machine learning (ML) algorithms cannot be viewed as gradient descent on some single objective. The solution trajectories taken by these algorithms naturally exhibit rotation, sometimes forming cycles, a behavior that is not expected with (full-batch) gradient descent. However, these algorithms can be viewed more generally as solving for the equilibrium of a game with possibly multiple competing objectives. Moreover, some recent ML models, specifically generative adversarial net- works (GANs) and its variants, are now explicitly formulated as equilibrium problems. Equilibrium problems present challenges beyond those encountered in optimization such as limit-cycles and chaotic attractors and are able to abstract away some of the difficulties encountered when training models like GANs. In this thesis, I aim to advance our understanding of equilibrium problems so as to improve state-of-the-art in GANs and related domains. In the following chapters, I will present work on 1. designing a no-regret framework for solving monotone equilibrium problems in online or streaming settings (with applications to Reinforcement Learning), 2. ensuring convergence when training a GAN to fit a normal distribution to data by Crossing-the-Curl, 3. improving state-of-the-art image generation with techniques derived from the- ory, 4. and borrowing tools from dynamical systems theory for analyzing the complex dynamics of GAN training.

关键词： artificial intelligence and robotics Dynamical Systems

来源：评论

学校读者我要写书评

暂无评论

The Use of Cultural Algorithms to Learn the Impact of Climate on Local Fishing Behavior in Cerro Azul, Peru

The Use of Cultural Algorithms to Learn the Impact of Climat...

引用

作者： Kattan, Khalid Wayne State University

学位级别：Ph.D.

Recently it has been found that the earth’s oceans are warming at a pace that is 40% faster than predicted by a United Nations panel a few years ago. As a result, 2019 has become the warmest year on record for the earth’s oceans. That is because the oceans have acted as a buffer by absorbing 93% of the heat produced by the greenhouse gases [40]. The impact of the oceanic warming has already been felt in terms of the periodic warming of the Pacific Ocean as an effect of the ENSO process. The ENSO process is a cycle of warming and subsequent cooling of the Pacific Ocean that can last over a period of years. This cycle was first documented by Peruvian fishermen in the early 1600’s. So it has been part of the environmental challenges that have been presented to economic agents throughout the world since then. It has even been suggested that the cycle has increased in frequency over the years, perhaps in response to the overall issues related to global warming. Although the onset of the ENSO cycle might be viewed as disruption of the fishing economy in a given area, there is some possibility that over time agents have been able to develop strategic responses to these changes to as to reduce the economic risk associated with them. During that time the Cerro Azul, Peru was in the process of emerging from one of the largest ENSOs on record. This was perceived to be a great opportunity to see how the collective bodies of fishermen were able to alter their fishing strategies to deal with these more uncertain times. Our results suggest that indeed the collective economic response of the fishermen demonstrates an ability to respond to the unpredictabilities of climate change, but at a cost. It is clear that the fishermen have gained the collective knowledge over the years to produce a coordinated response that can be observed at a higher level. Of course, this knowledge can be used to coordinate activities only if it is communicated socially within the society. Although our dat

关键词： Climate Change Cultural Algorithms Evolutionary Algorithms Machine Learning Multi-Objective Optimization Nonlinear Regression artificial intelligence and robotics Computer Sciences History of Art, Architecture, and Archaeology

来源：评论

学校读者我要写书评

暂无评论

Machine intelligence For Advanced Medical Data Analysis: Manifold Learning Approach

Machine Intelligence For Advanced Medical Data Analysis: Man...

引用

作者： Fereshteh S Bashiri University of Wisconsin – Milwaukee

学位级别：博士

In the current work, linear and non-linear manifold learning techniques, specifically Principle Component Analysis (PCA) and Laplacian Eigenmaps, are studied in detail. Their applications in medical image and shape analysis are investigated. In the first contribution, a manifold learning-based multi-modal image registration technique is developed, which results in a unified intensity system through intensity transformation between the reference and sensed images. The transformation eliminates intensity variations in multi-modal medical scans and hence facilitates employing well-studied mono-modal registration techniques. The method can be used for registering multi-modal images with full and partial data. Next, a manifold learning-based scale invariant global shape descriptor is introduced. The proposed descriptor benefits from the capability of Laplacian Eigenmap in dealing with high dimensional data by introducing an exponential weighting scheme. It eliminates the limitations tied to the well-known cotangent weighting scheme, namely dependency on triangular mesh representation and high intra-class quality of 3D models. In the end, a novel descriptive model for diagnostic classification of pulmonary nodules is presented. The descriptive model benefits from structural differences between benign and malignant nodules for automatic and accurate prediction of a candidate nodule. It extracts concise and discriminative features automatically from the 3D surface structure of a nodule using spectral features studied in the previous work combined with a point cloud-based deep learning network. Extensive experiments have been conducted and have shown that the proposed algorithms based on manifold learning outperform several state-of-the-art methods. Advanced computational techniques with a combination of manifold learning and deep networks can play a vital role in effective healthcare delivery by providing a framework for several fundamental tasks in image and shape processi

关键词： Deep learning Descriptive model Image Processing Manifold learning Spectral analysis artificial intelligence and robotics Computer Sciences Electrical and Electronics

来源：评论

学校读者我要写书评

暂无评论

Tools for Tutoring Theoretical Computer Science Topics

Tools for Tutoring Theoretical Computer Science Topics

引用

作者： Mark McCartin-Lim University of Massachusetts Amherst

学位级别：博士

This thesis introduces COMPLEXITY TUTOR, a tutoring system to assist in learning abstract proof-based topics, which has been specifically targeted towards the population of computer science students studying theoretical computer science. Existing literature has shown tremendous educational benefits produced by active learning techniques, student-centered pedagogy, gamification and intelligent tutoring systems. However, previously, there had been almost no research on adapting these ideas to the domain of theoretical computer science. As a population, computer science students receive immediate feedback from compilers and debuggers, but receive no similar level of guidance for theoretical coursework. One hypothesis of this thesis is that immediate feedback while working on theoretical problems would be particularly well-received by students, and this hypothesis has been supported by the feedback of students who used the system. This thesis makes several contributions to the field. It provides assistance for teaching proof construction in theoretical computer science. A second contribution is a framework that can be readily adapted to many other domains with abstract mathematical content. Exercises can be constructed in natural language and instructors with limited programming knowledge can quickly develop new subject material for COMPLEXITY TUTOR. A third contribution is a platform for writing algorithms in Python code that has been integrated into this framework, for constructive proofs in computer science. A fourth contribution is development of an interactive environment that uses a novel graphical puzzle-like platform and gamification ideas to teach proof concepts. The learning curve for students is reduced, in comparison to other systems that use a formal language or complex interface. A multi-semester evaluation of 101 computer science students using COMPLEXITY TUTOR was conducted. An additional 98 students participated in the study as part of control groups. C

关键词： artificial intelligence and robotics Graphics and Human Computer Interfaces Other Computer Sciences Theory and Algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards IoT-Aided Human-Robot Interaction Using NEP and ROS: A Platform-Independent, Accessible and Distributed Approach

引用

SENSORS 2020年第5期20卷 1500-1500页

作者： Coronado, Enrique Venture, Gentiane Tokyo Univ Agr & Technol Dept Mech Syst Engn Tokyo 1840012 Japan

This article presents the novel Python, C# and JavaScript libraries of Node Primitives (NEP), a high-level, open, distributed, and component-based framework designed to enable easy development of cross-platform software architectures. NEP is built on top of low-level, high-performance and robust sockets libraries (ZeroMQ and Nanomsg) and robot middlewares (ROS 1 and ROS 2). This enables platform-independent development of Human-Robot Interaction (HRI) software architectures. We show minimal code examples for enabling Publish/Subscribe communication between Internet of Things (IoT) and robotics modules. Two user cases performed outside laboratories are briefly described in order to prove the technological feasibility of NEP for developing real-world applications. The first user case briefly shows the potential of using NEP for enabling the creation of End-User Development (EUD) interfaces for IoT-aided Human-Robot Interaction. The second user case briefly describes a software architecture integrating state-of-art sensory devices, deep learning perceptual modules, and a ROS -based humanoid robot to enable IoT-aided HRI in a public space. Finally, a comparative study showed better latency results of NEP over a popular state-of-art tool (ROS using rosbridge) for connecting different nodes executed in local-host and local area network (LAN).

关键词： internet of robot things artificial intelligence and robotics human-computer interaction human-robot interaction

来源：评论

学校读者我要写书评

暂无评论

FUNCTION AND DISSIPATION IN FINITE STATE AUTOMATA - FROM COMPUTING TO intelligence AND BACK

FUNCTION AND DISSIPATION IN FINITE STATE AUTOMATA - FROM COM...

引用

作者： Natesh Ganesh University of Massachusetts Amherst

学位级别：博士

Society has benefited from the technological revolution and the tremendous growth in computing powered by Moore's law. However, we are fast approaching the ultimate physical limits in terms of both device sizes and the associated energy dissipation. It is important to characterize these limits in a physically grounded and implementation-agnostic manner, in order to capture the fundamental energy dissipation costs associated with performing computing operations with classical information in nano-scale quantum systems. It is also necessary to identify and understand the effect of quantum in-distinguishability, noise, and device variability on these dissipation limits. Identifying these parameters is crucial to designing more energy efficient computing systems moving forward. In this dissertation, we will provide a physical description of finite state automaton, an abstract tool commonly used to describe computational operations under the Referential Approach to physical information theory. We will derive the fundamental limits of dissipation associated with a state transition in deterministic and probabilistic finite state automaton, and propose efficacy measures to capture how well a particular state transition has been physically realized. We will use these dissipation bounds to understand the limits of dissipation during learning during training and testing phases in feed-forward and recurrent neural networks. This study of dissipation in neural network provides key hints at how dissipation is fundamentally intertwined with learning in physical systems. These ideas connecting energy dissipation, entropy and physical information provide the perfect toolkit to critically analyze the very foundations of computing, and our computational approaches to artificial intelligence. In the second part of this dissertation, we derive the non-equilibrium reliable low dissipation condition for predictive inference in self-organized systems. This brings together the central ideas

关键词： artificial intelligence and robotics Nanoscience and Nanotechnology Other Computer Engineering Other Computer Sciences Other Electrical and Computer Engineering Other Neuroscience and Neurobiology Other Physics Power and Energy Probability Theory and Algorithms

来源：评论

学校读者我要写书评

暂无评论

Limits Of Model Selection, Link Prediction, And Community Detection

Limits Of Model Selection, Link Prediction, And Community De...

引用

作者： Amir Ghasemian University of Colorado

学位级别：博士

Relational data has become increasingly ubiquitous nowadays. Networks are very rich tools in graph theory, which represent real world interactions through a simple abstract graph, including nodes and edges. Network analysis and modeling has gained extremely wide attentions from the researchers in various disciplines, such as computer science, social science, biology, economics, electrical engineering, and physics. Network analysis is the study of the network topology to answer a variety of application-based questions regarding the original real world problem. For example in social network analysis the questions are related to how people interact with each other in online social networks, or in collaboration networks, how diseases propagate or how information flows through a network, or how to control a disease or food outbreak. In electric networks like power grids or in internet networks, the questions can be related to vulnerability assessment of the networks to be prepared for power outage or internet blackout. In biological network analysis, the questions are related to how different diseases are related to each other, which can be useful in discovering new symptoms of diseases and producing and developing new medicines. It appears clearly that the reason of the importance of this interdisciplinary area of science, is due to its widespread applications which involves scientists and researchers with a variety of background and interests. Although networks are much simpler compared to the original complex systems, the interactions among the nodes in the real-world network may seem random, and capturing patterns on these entities is not trivial. There are tremendous questions about inference on networks, which makes this topic very attractive for researchers in the field. In this dissertation we answer some of the questions regarding this topic in two lines of study: one focused on experimental analyses and one focused on theoretical limitations. In Chapter 2 we lo

关键词： community detection link description link prediction model selection overfitting underfitting artificial intelligence and robotics Computer Sciences

来源：评论

学校读者我要写书评

暂无评论

Probabilistic Spiking Neural Networks: Supervised, Unsupervised and Adversarial Trainings

Probabilistic Spiking Neural Networks: Supervised, Unsupervi...

引用

作者： Bagheri, Alireza New Jersey Institute of Technology

学位级别：Ph.D.

Spiking Neural Networks (SNNs), or third-generation neural networks, are networks of computation units, called neurons, in which each neuron with internal analogue dynamics receives as input and produces as output spiking, that is, binary sparse, signals. In contrast, second-generation neural networks, termed as artificial Neural Networks (ANNs), rely on simple static non-linear neurons that are known to be energy-intensive, hindering their implementations on energy-limited processors such as mobile devices. The sparse event-based characteristics of SNNs for information transmission and encoding have made them more feasible for highly energy-efficient neuromorphic computing architectures. The most existing training algorithms for SNNs are based on deterministic spiking neurons that limit their flexibility and expressive power. Moreover, the SNNs are typically trained based on the back-propagation method, which unlike ANNs, it becomes challenging due to the non-differentiability nature of the spike dynamics. Considering these two key issues, this dissertation is devoted to develop probabilistic frameworks for SNNs that are tailored to the solution of supervised and unsupervised cognitive tasks. The SNNs utilize rich model, flexible and computationally tractable properties of Generalized Linear Model (GLM) neuron. The GLM is a probabilistic neural model that was previously considered within the computational neuroscience literature. A novel training method is proposed for the purpose of classification with a first-to-spike decoding rule, whereby the SNN can perform an early classification decision once spike firing is detected at an output neuron. This method is in contrast with conventional classification rules for SNNs that operate offline based on the number of output spikes at each output neuron. As a result, the proposed method improves the accuracy-inference complexity trade-off with respect to conventional decoding. For the first time in the field, the sensitiv

关键词： Adversarial learning Generalized linear model Neuromorphic Spiking neural network Supervised learning Unsupervised learning artificial intelligence and robotics Computer Sciences Electrical and Electronics

来源：评论

学校读者我要写书评

暂无评论

Allocative Poisson Factorization for Computational Social Science

Allocative Poisson Factorization for Computational Social Sc...

引用

作者： Aaron Schein University of Massachusetts Amherst

学位级别：博士

Social science data often comes in the form of high-dimensional discrete data such as categorical survey responses, social interaction records, or text. These data sets exhibit high degrees of sparsity, missingness, overdispersion, and burstiness, all of which present challenges to traditional statistical modeling techniques. The framework of Poisson factorization (PF) has emerged in recent years as a natural way to model high-dimensional discrete data sets. This framework assumes that each observed count in a data set is a Poisson random variable $y ~ Pois(\mu)$ whose rate parameter $\mu$ is a function of shared model parameters. This thesis examines a specific subset of Poisson factorization models that constrain $\mu$ to be a multilinear function of shared model parameters. This subset of models---hereby referred to as allocative Poisson factorization (APF)---enjoys a significant computational advantage: posterior inference scales linearly with only the number of non-zero counts in the data set. A challenge to constructing and performing inference in APF models is that the multilinear constraint on $\mu$---which must be non-negative, by the definition of the Poisson distribution---means that the shared model parameters must themselves be non-negative. Constructing models that capture the complex dependency structures inherent to social processes---e.g., networks with overlapping communities of actors or bursty temporal dynamics---without relying on the analytic convenience and tractability of the Gaussian distribution requires novel constructions of non-negative distributions---e.g., gamma and Dirichlet---and innovative posterior inference techniques. This thesis presents the APF analogue to several widely-used models---i.e., CP decomposition (Chapter 3), Tucker decomposition (Chapter 4), and linear dynamical systems (Chapters 5 and 6) and shows how to perform Bayesian inference in APF models under local differential privacy (Chapter 7). Most of these chapters in

关键词： Applied Statistics artificial intelligence and robotics Categorical Data Analysis International Relations Probability Statistical Methodology Statistical Models

来源：评论

学校读者我要写书评

暂无评论

Efficient Self-supervised Deep Sensorimotor Learning in robotics

Efficient Self-supervised Deep Sensorimotor Learning in Robo...

引用

作者： Takeshi Takahashi University of Massachusetts Amherst

学位级别：博士

Deep learning has been successful in a variety of applications, such as object recognition, video games, and machine translation. Deep neural networks can automatically learn important features given large training datasets. However, the success of deep learning in robotic systems in the real world is still limited mainly because obtaining large datasets and labeling are costly. As a result, much of the successful work in deep learning has been limited to domains where large datasets are readily available or easily collected. To address this issue, I propose a framework for acquiring re-usable skills efficiently combining intrinsic motivation and the control basis framework --- a developmental architecture implemented using a landscape of attractors. A deep neural classifier is used to predict probabilistic control affordances representing controller states accessible by way of actions. Information theoretic motivation with embedding distance influences exploration in a way that supports learning control affordances efficiently. The learned affordance is used as a filter to help a robot experience more positive outcomes of controllers when a robot learns a new affordance. I conduct quantitative experiments using a dynamic simulator and the results show that the proposed learning framework enables a mobile manipulator to learn deep sensorimotor skills more efficiently in a self-supervised learning manner.

关键词： artificial intelligence and robotics Computer Sciences

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：