Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 48 for “"neural network training"”.
-
Optimizing Graph Neural Network Training on Large Graphs
… prediction and node property prediction. Graph Neural Network models demonstrate good performance on such tasks. However, the depth of the models and the size of the graphs they can be trained on is constrained either by the low processing throughput of CPUs or by the limited memory capacity of …
-
Accelerating distributed neural network training with network-centric approach
Distributed training of Deep Neural Networks (DNN) is an important technique to reduce the training time of large DNNs for a wide range of applications. In existing distributed training approaches, however, the communication time to periodically exchange parameters (i.e., weights) and gradients …
-
Empirical Approaches to Challenges in Neural Network Training and Deployment
Training and deploying neural networks is a challenging endeavor. During the training phase, we need to decide on what optimizer to use, the exact data to train on, the training curriculum, and many other factors-- all of which affect the final performance. Once the model is trained, we need to …
-
Neural Network Training and Inversion with a Bregman Learning Framework
Deep Neural Networks (DNNs) are powerful computing systems that have revolutionised a wide range of research domains and have achieved remarkable success in various realworld applications over the past decade. Despite their significant recent advancements, training DNNs still remains a challenging …
-
Enhanced Neural Network Training Using Selective Backpropagation and Forward Propagation
Neural networks are making headlines every day as the tool of the future, powering artificial intelligence programs and supporting technologies never seen before. However, the training of neural networks can take days or even weeks for bigger networks, and requires the use of super computers and …
-
Optimizing Graph Neural Network Training on Large Graphs in A Distributed Setting
Graph neural networks (GNNs) are an important class of methods for leveraging the information present in graph structures to perform various learning tasks. Distributed GNNs can improve the performance of GNN execution by dividing computation among multiple machines and scale to large graphs by …
-
Accelerating Distributed Deep Neural Network Training and Fine-Tuning Through Resource Interleaving
… overhead of distributed Machine Learning (ML) training and fine-tuning workloads quickly takes up a significant portion of iteration time. Yet state-of-the-art ML schedulers tend to ignore the communication pattern of ML jobs when placing workers on GPUs. This thesis advocates for …
-
A Deterministic Approach to Partitioning Neural Network Training Data for the Classification Problem
… have been developed. For business applications, neural networks have become the most commonly used classification technique and though they often outperform traditional statistical classification methods, their performance may be hindered because of failings in the use of training data. This …
-
Perspectives on Geometry and Optimization: from Measures to Neural Networks
… point methods, unbalanced optimal transport, and neural network training. We use these examples to illustrate four ways in which geometry plays key yet fundamentally different roles in optimization. The first part explores the benign properties of exploiting the intrinsic symmetries in matrix …
-
Devices and Algorithms for Analog Deep Learning
… a near-ideal device technology and a superior neural network training algorithm that can ultimately propel analog computing when combined together. The CMOS-compatible nanoscale protonic devices demonstrated here show unprecedented characteristics, incorporating the benefits of nanoionics with …
-
Voice Control of Fetch Robot Using Amazon Alexa
… object. The follow model was also learned by Neural Network training, which allows for the target position to be predicted in future maps.
-
Proposing effective coordinate search methods for solving large-scale expensive black-box optimization problems
… tested on the CEC-2013 benchmarks problems and neural network training.
-
A Deep Learning and Signal Processing Architecture Using Frequency-Encoded RF Photonics
Deep neural networks have become ubiquitous due to their ability to perform arbitrary tasks more accurately than manually-crafted systems. This ability has created a substantial demand for more complex models processing larger amounts of data. However, the traditional computing architecture has …
-
Construction of a superconducting circuit simulator and its applications in cryogenic computing
… to design a superconducting nanowire based deep neural network training accelerator. I design, implement, and characterize a unit cell for this application. These local processors have significant device-level advantages over the readily available non-volatile memory technologies in realizing …
-
On the Inductive Biases of Conditional Diffusion Models
… in regions outside the support of the training data. We observe that neural networks are capable of learning qualitatively different forms of interpolation, which may be influenced by the architecture and capacity of the network and other aspects of neural network training. We develop a …
-
CausalSim: Toward A Causal Data-Driven Simulator For Network Protocols
Evaluating the real-world performance of network protocols is challenging. Randomized control trials (RCT) are expensive and inaccessible to most researchers, while expert-designed simulators fail to capture complex behaviors in real networks. We present CausalSim, a data-driven simulator for …
-
Artificial Neural Networks as a Probe of Many-Body Localization in Novel Topologies
We attempt to show that artificial neural networks may be used as a tool for universal probing of many-body localization in quantum graphs. We produce an artificial neural network, training it on the entanglement spectra of the nearest-neighbour Heisenberg spin1/2 chain in the presence of extremal …
-
Optimization Theory and Machine Learning Practice: Mind the Gap
… many machine learning pipelines including neural network training, which will be our main testing ground for theoretical analyses in this thesis. Among different kinds of optimization algorithms, gradient methods have become the dominant algorithms in deep learning due to their scalability …
-
Learning generalizable device placement algorithms for distributed machine learning
… find device placements for distributed neural network training. Unlike prior approaches that only find a device placement for a specific computation graph, Placeto can learn generalizable device placement policies that can be applied to any graph. We propose two key ideas in our …
-
Accelerated algorithms for constrained optimization and control
… academic examples, power flow optimization and neural network optimization. We devote special attention to analyze a special case of neural network optimization, namely, linear neural network training problem, to understand the dynamics of nonconvex optimization governed by gradient flow and …
Page 1 of 3