Browsing Division of Electrical, Electronics, and Computer Science (EECS) by Subject "Machine Learning"
Now showing items 21-36 of 36
-
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 ... -
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 ... -
Protecting Deep Learning Models on Cloud Platforms with Trusted Execution Environments
Deep learning is rapidly integrated into different applications, from medical imaging to financial products. Organisations are spending enormous financial resources to train deep learning models. Often, many organisations ... -
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 ... -
Representing Networks: Centrality, Node Embeddings, Community Outliers and Graph Representation
Networks are ubiquitous. We start our technical work in this thesis by exploring the classical concept of node centrality (also known as influence measure) in information networks. Like clustering, node centrality is also ... -
Robust Distribution-Free Learning Of Logic Expressions
(2012-05-24) -
Sparse Bayesian Learning For Joint Channel Estimation Data Detection In OFDM Systems
(2018-08-30)Bayesian approaches for sparse signal recovery have enjoyed a long-standing history in signal processing and machine learning literature. Among the Bayesian techniques, the expectation maximization based Sparse Bayesian ... -
Sparse Input View Synthesis: 3D Representations and Reliable Priors
Novel view synthesis refers to the problem of synthesizing novel viewpoints of a scene given the images from a few viewpoints. This is a fundamental problem in computer vision and graphics, and enables a vast variety of ... -
Sparse Multiclass And Multi-Label Classifier Design For Faster Inference
(2013-06-20)Many real-world problems like hand-written digit recognition or semantic scene classification are treated as multiclass or multi-label classification prob-lems. Solutions to these problems using support vector machines (SVMs) ... -
Speech Based Low-Complexity Classification of Patients with Amyotrophic Lateral Sclerosis from Healthy Controls: Exploring the Role of Hypernasality
Amyotrophic Lateral Sclerosis (ALS) is a neurodegenerative disorder characterized by motor neuron degeneration, leading to muscle weakness, atrophy, and speech impairments. Dysarthria, an early symptom in approximately 30% ... -
Studies In Automatic Management Of Storage Systems
(2015-11-16)Autonomic management is important in storage systems and the space of autonomics in storage systems is vast. Such autonomic management systems can employ a variety of techniques depending upon the specific problem. In this ... -
Temporal Point Processes for Forecasting Events in Higher-Order Networks
Real-world systems consisting of interacting entities can be effectively represented as time-evolving networks or graphs, where the entities are depicted as nodes, and the interactions between them are represented as ... -
Tight Frames, Non-convex Regularizers, and Quantized Neural Networks for Solving Linear Inverse Problems
The recovery of a signal/image from compressed measurements involves formulating an optimization problem and solving it using an efficient algorithm. The optimization objective involves data fidelity, which is responsible ...