Browsing by Subject "Machine Learning"
Now showing items 21-40 of 49
-
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 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 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 ... -
Low Power Machine Learning Systems for Energy Efficient Edge Devices
Energy-efficient devices are essential in the world of edge computing and the tiny Machine Learning (tinyML) paradigm. Edge devices are often constrained by the available compu- tational power and hardware resource. To ... -
Machine Learning Algorithms Using Classical And Quantum Photonics
ABSTRACT In the modern day , we are witnessing two complementary trends, exponential growth in data and shrinking of chip size. The Data is approaching to 44 zettabytes by 2020 and the chips are now available with 10nm ... -
Machine learning and density functional theory assisted insights into the mechanical and oxidation properties of nickel-based superalloys
Due to global warming and increasing fuel costs, there is a constant thrust toward increasing fuel efficiency and reducing the emissions of gas-turbine engines, which are made out of superalloys. New superalloy materials, ... -
Malware Analysis using Profile Hidden Markov Models and Intrusion Detection in a Stream Learning Setting
(2018-02-18)In the last decade, a lot of machine learning and data mining based approaches have been used in the areas of intrusion detection, malware detection and classification and also traffic analysis. In the area of malware ... -
Methods for Improving Data-efficiency and Trustworthiness using Natural Language Supervision
Traditional strategies to build machine learning based classification systems employ discrete labels as targets. This limits the usefulness of such systems in two ways. First, the generalizability of these systems is limited ... -
Model Extraction and Active Learning
Machine learning models are increasingly being offered as a service by big companies such as Google, Microsoft and Amazon. They use Machine Learning as a Service (MLaaS) to expose these machine learning models to the ... -
Model Reference Learning Control Using ANFIS
(2012-05-25) -
Multi-label Classification with Multiple Label Correlation Orders And Structures
(2018-06-18)Multilabel classification has attracted much interest in recent times due to the wide applicability of the problem and the challenges involved in learning a classifier for multilabeled data. A crucial aspect of multilabel ... -
Novel First-order Algorithms for Non-smooth Optimization Problems in Machine Learning
This thesis is devoted to designing efficient optimization algorithms for machine learning (ML) problems where the underlying objective function to be optimized is convex but not necessarily differentiable. Such non-smooth ... -
Nuclear quantum effects in gas-phase systems with large amplitude motions: A study of 2-fluoroethanol, ethylene glycol, and H3O2
This thesis explores the role of nuclear quantum effects in selected systems containing large amplitude motion through path integral simulations. Recent works have explored molecules with such floppy modes and examined ... -
On Leveraging Dynamic Processes in Large Social Networks for Smart Cities
The concept of smart city which began as being synonymous with electronically networked community underwent significant changes with the growth in mobile devices and social networking. This expanded the outlook of smart ... -
On the Optimality of Generative Adversarial Networks — A Variational Perspective
Generative adversarial networks (GANs) are a popular learning framework to model the underlying distribution of images. GANs comprise a min-max game between the generator and the discriminator. While the generator transforms ... -
Optimization Algorithms for Deterministic, Stochastic and Reinforcement Learning Settings
(2018-05-30)Optimization is a very important field with diverse applications in physical, social and biological sciences and in various areas of engineering. It appears widely in ma-chine learning, information retrieval, regression, ... -
Performance Characterization and Optimizations of Traditional ML Applications
Even in the era of Deep Learning based methods, traditional machine learning methods with large data sets continue to attract significant attention. However, we find an apparent lack of a detailed performance characterization ... -
Prompt and Displaced Signatures of Physics Beyond the Standard Model
The quest to understand our Universe’s fundamental particles and their interactions has led us to the Standard Model (SM) of particle physics. Despite successfully explaining the weak, electromagnetic, and strong ... -
Provable Methods for Non-negative Matrix Factorization
(2017-10-31)Nonnegative matrix factorization (NMF) is an important data-analysis problem which concerns factoring a given d n matrix A with nonnegative entries into matrices B and C where B and C are d k and k n with nonnegative ... -
Relating Representations in Deep Learning and the Brain
Deep Neural Networks (DNN) inspired by the human brain have redefined the state-of-the-art performance in AI during the past decade. Much of the research is still trying to understand and explain the function of these ...