Browsing by Title
Now showing items 3950-3969 of 8429
-
Learning Across Domains: Applications to Text-based Person Search and Multi-Source Domain Adaptation
With rapid development in technology and ubiquitous presence of diverse types of sensors, a large amount of data from different modalities (e.g., text, audio, images etc.) describing the same person/ object/event has ... -
Learning Action Priors for Deep Visual Predictions
This thesis addresses the critical challenge of visual prediction in mobile robotics, particularly focusing on scenarios where cameras mounted on autonomous robots must navigate dynamic environments with human presence. ... -
Learning Algorithms for stochastic automata-
Reported in this thesis is the study of nonlinear learning algorithms or reinforcement schemes for multi-state stochastic automata acting in stationary random media with unknown response characteristics. Such stochastic ... -
Learning Algorithms Using Chance-Constrained Programs
(2010-07-08)This thesis explores Chance-Constrained Programming (CCP) in the context of learning. It is shown that chance-constraint approaches lead to improved algorithms for three important learning problems — classification with ... -
Learning Compact Architectures for Deep Neural Networks
(2018-05-22)Deep neural networks with millions of parameters are at the heart of many state of the art computer vision models. However, recent works have shown that models with much smaller number of parameters can often perform just ... -
Learning Decentralized Goal-Based Vector Quantization
(2012-05-04) -
Learning Dynamic Prices In Electronic Markets
(2011-04-19) -
Learning Filters, Filterbanks, Wavelets and Multiscale Representations
The problem of filter design is ubiquitous. Frequency selective filters are used in speech/audio processing, image analysis, convolutional neural networks for tasks such as denoising, deblurring/deconvolution, enhancement, ... -
Learning From Examples Using Hierarchical Counterfactual Expressions
In this study, we develop algorithms for learning concepts from examples. Learning is the capability that allows a system to improve its performance. It involves the ability to correct errors, learn domain knowledge, ... -
Learning from Limited and Imperfect Data
Deep Neural Networks have demonstrated orders of magnitude improvement in capabilities over the years after AlexNet won the ImageNet challenge in 2012. One of the major reasons for this success is the availability of ... -
Learning Invariants for Verification of Programs and Control Systems
Deductive verification techniques in the style of Floyd and Hoare have the potential to give us concise, compositional, and scalable proofs of the correctness of various kinds of software systems like programs and control ... -
Learning Multiple Initial Conditions using Physics Informed Neural Networks
Physics-Informed Neural Networks (PINNs) and its variants have emerged as a tool for solving differential equations in the past few years. Although several variants of PINNs have been proposed, the majority of these ... -
Learning Non-linear Mappings from Data with Applications to Priority-based Clustering, Prediction, and Detection
With the volume of data generated in today's internet-of-things, learning algorithms to extract and understand the underlying relations between the various attributes of data have gained momentum. This thesis is focused ... -
Learning Robust Support Vector Machine Classifiers With Uncertain Observations
(2015-08-19)The central theme of the thesis is to study linear and non linear SVM formulations in the presence of uncertain observations. The main contribution of this thesis is to derive robust classfiers from partial knowledge of ... -
Learning subspace methods using weighted and multi-subspace representations
The learning subspace methods (LSMs) of classification are decision-theoretic pattern recognition methods where the primary model for a class is a linear subspace of the Euclidean pattern space. Classification is based on ... -
Learning to Adapt Policies for uSD card
Machine Learning(ML) for Systems is a new and promising research area where performance of computer systems is optimized using machine learning methods. ML for Systems has outperformed traditional heuristics methods in ... -
Learning to Perceive Humans From Appearance and Pose
Analyzing humans and their activities takes a central role in computer vision. This requires machine learning models to encapsulate both the diverse poses and appearances exhibited by humans. Estimating the 3D poses of ... -
Learning Tournament Solutions from Preference-based Multi-Armed Bandits
We consider the dueling bandits problem, a sequential decision task where the goal is to learn to pick `good' arms out of an available pool by actively querying for and observing relative preferences between selected pairs ... -
Learning with Complex Performance Measures : Theory, Algorithms and Applications
(2017-12-07)We consider supervised learning problems, where one is given objects with labels, and the goal is to learn a model that can make accurate predictions on new objects. These problems abound in applications, ranging from ... -
Learning with Multi-domain and Multi-view Graph Data
In many applications, we observe large volumes of data supported on irregular (non-Euclidean) domains. In graph signal processing (GSP) and graph machine learning (GML), data is indexed using the nodes of a graph and ...