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 29 for “"model compression"”.
-
Model Compression and AutoML for Efficient Click-Through Rate Prediction
… response for recommender systems. However, these model architectures are often effective at the cost of large computational, and memory, cost. This limits their ability to run on edge devices with smaller hardwares, such as smartphones, which is a popular use case for recommender systems. We …
-
Mathematical Optimization Algorithms for Model Compression and Adversarial Learning in Deep Neural Networks
… and self-driving cars. However, their large model size and computational requirements add a significant burden to state-of-the-art computing systems. Weight pruning is an effective approach to reduce the model size and computational requirements of DNNs. However, prior works in this area are …
-
Information-theoretic bounds in learning algorithms
… in practice, we then study the problem of model change detection. There are two sets of samples that are generated according to a pre-change probabilistic model with parameter theta, and a post-change model with parameter theta', respectively. The goal is to detect whether the change in the …
-
Learning with generalized negative dependence : probabilistic models of diversity for machine learning
… learning problems that require a theoretical model of diversification. Examples of such problems include experimental design and model compression: subset-selection problems that require carefully balancing the quality of each selected element with the diversity of the subset as a whole. …
-
Software-Hardware Co-design For Deep Learning Model Acceleration
<p>Current deep neural network (DNN) models have shown beyond-human performance in multiple artificial intelligent tasks. However, state-of-the-art DNN models still exhibit great issues on efficiency that pose significant obstacles to their practical application in real-world scenarios. To further …
-
Energy-aware DNN Quantization for Processing-In-Memory Architecture
… proposed from dedicated hardware platforms to model compression algorithms. Recently, hardware-aware quantization algorithms have shown further improvement in the energy efficiency of DNN by considering hardware architectures and algorithms together. In this work, a genetic algorithm-based …
-
FairML : ToolBox for diagnosing bias in predictive modeling
Predictive models are increasingly deployed for the purpose of determining access to services such as credit, insurance, and employment. Despite societal gains in efficiency and productivity through deployment of these models, potential systemic flaws have not been fully addressed, particularly the …
-
MODEL ADAPTATION FOR EDGE AI
… due to their computational demands. Existing model compression techniques often fall short by being oblivious to downstream user-specific tasks. This thesis addresses the challenge of adapting DNN models effectively on resource-limited hardware, advocating for flexible and efficient models. …
-
Hardware software co-design of machine learning accelerators using univariate functions
… techniques for hardware-awaretraining and model compression using univariate functions. First, we optimize hardware using a simple constant coefficient multiplier on Hybrid Binary-Unary (HBUNN) architecture, which offers variable hardware costs for constant coefficients. By applying …
-
Information theory meets big data: Theory, algorithms and applications to deep learning
… tools to improve training algorithms and model compression algorithms in deep learning.
-
Privacy-aware Federated Learning with Global Differential Privacy
… communication reduction techniques, namely, model compression, partial device participation, and periodic aggregation. Furthermore, the convergence of federated learning systems is also affected by data heterogeneity. Federated learning systems are capable of protecting the private data of …
-
Neuromorphic Systems for Pattern Recognition and Uav Trajectory Planning
… performance of a recurrent belief propagation model. We first develop a probabilistic inference network to post process the recognition results of deep Convolutional Neural Network (CNN) (e.g. LeNet) and collect individual characters to form words. The output of the inference network is a set …
-
Neuromorphic Systems For Pattern Recognition And Uav Trajectory Planning
… performance of a recurrent belief propagation model. We first develop a probabilistic inference network to post process the recognition results of deep Convolutional Neural Network (CNN) (e.g. LeNet) and collect individual characters to form words. The output of the inference network is a set …
-
Scaling Laws for Deep Learning
… governed by scaling laws — for state of the art models and tasks, spanning image classification and language modeling, as well as for state of the art model compression via iterative pruning. Predictability, via the establishment of these scaling laws, provides the path for principled design and …
-
Taming TinyML: deep learning inference at computational extremes
The advanced data modelling capabilities of neural networks allowed deep learning to become a cornerstone of many applications of artificial intelligence (AI). AI can be brought into our environments by deploying neural models to ubiquitous Internet-of-Things (IoT), wearable and embedded devices to …
-
TwinDNN: A tale of two deep neural networks
Compression technologies for deep neural networks (DNNs), such as weight quantization, have been widely investigated to reduce the model size so that they can be implemented on hardware with strict resource restrictions. However, one major disadvantage of model compression is accuracy degradation. …
-
Exploring Accumulated Gradient-Based Quantization and Compression for Deep Neural Networks
… also achieving significant pruning, leading to model compression. We use the total accumulated absolute gradient over the training process as the indicator of importance of a parameter to the network. The most important parameters are quantized by the smallest amount. The post-training …
-
Advances in Compression using Probabilistic Models
… and storage necessitate the use of efficient compression methods. Compression algorithms work by mapping data to a more compact representation from which the original data can be recovered. To operate efficiently, they need to capture the characteristics of the data distribution, which can be …
-
Co-Designing Efficient Systems and Algorithms for Sparse and Quantized Deep Learning Computing
Deep learning models are becoming increasingly complex, expanding from 1D text and 2D images to 3D point clouds, while their size continues to grow exponentially. This trend highlights the need for greater efficiency. This thesis systematically explores efficiency in two resource-intensive …
Page 1 of 2