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 470 for “"deep neural networks"”.
-
Towards Robust Deep Neural Networks
Deep neural networks (DNNs) enable state-of-the-art performance for most machine learning tasks. Unfortunately, they are vulnerable to attacks, such as Trojans during training and Adversarial Examples at test time. Adversarial Examples are inputs with carefully crafted perturbations added to benign …
-
Dissection of Deep Neural Networks
… of neurons within the internal computations of deep neural networks for computer vision. We introduce network dissection, a method for quantifying the alignment between human-interpretable visual concepts and individual neurons in a deep network. We apply network dissection to examine and …
-
Read alignment using deep neural networks
… alignment. In this research work, we train a Deep Neural Network (DNN) to yield a hashing scheme for the highly erroneous long reads, which is deemed superior to Minhash for mapping the reads. We implemented that idea to build a read alignment tool: DNNAligner. We evaluated the performance of …
-
Structural Priors in Deep Neural Networks
Deep learning has in recent years come to dominate the previously separate fields of research in machine learning, computer vision, natural language understanding and speech recognition. Despite breakthroughs in training deep networks, there remains a lack of understanding of both the optimization …
-
Parsimonious Principles of Deep Neural Networks
… the intrinsic simplicity bias exhibited by deep neural networks — the powerhouse of modern AI. By analyzing the effective rank of the learned representation kernels, we unveil the observation that these models have an inherent preference for learning parsimonious relationships in the data. …
-
On foveation of deep neural networks
… and existing state-of- the-art convolutional neural networks (CNNs), and are much more prominent in CNNs. We found many cases where CNNs classified one region correctly and the other incorrectly, though they only differed by one row or column of pixels, and were often bigger than the average …
-
Towards Biologically Plausible Deep Neural Networks
… data. Conversely, artificial intelligence, deep neural networks in particular, has contributed to advancing the understanding of the brain. Deep neural networks when trained adequately can reproduce behavioral and neural data better than previously developed models. Here we present studies …
-
Deep neural networks for choice analysis
As deep neural networks (DNNs) outperform classical discrete choice models (DCMs) in many empirical studies, one pressing question is how to reconcile them in the context of choice analysis. So far researchers mainly compare their prediction accuracy, treating them as completely different modeling …
-
Semantic Language models with deep neural Networks
… to suppress this noise we introduce the use of deep semantic encodings for semantic feature extraction. In this way, SELMs optimize both the recognition and the understanding performance.
-
Large-scale training of deep neural networks
Accelerating and scaling the training of deep neural networks (DNNs) is critical to keep up with growing datasets, reduce training times, and enable training on memory-constrained problems where parallelism is necessary. In this thesis, I present a set of techniques that can leverage large …
-
Audio super-resolution with deep neural networks
… reports various attempts at applying generative deep neural networks to audio for the task of recovering a high quality audio signal when given a low sample rate signal. Our experiments show that deep networks are able to discover patterns in speech and music signals by working in both time and …
-
Why deep neural networks for function approximation
… has been much interest in understanding why deep neural networks are preferred to shallow networks. We show that, for a large class of piecewise smooth functions, the number of neurons needed by a shallow network to approximate a function is exponentially larger than the corresponding number …
-
Structured Deep Neural Networks for Speech Recognition
Deep neural networks (DNNs) and deep learning approaches yield state-of-the-art performance in a range of machine learning tasks, including automatic speech recognition. The multi-layer transformations and activation functions in DNNs, or related network variations, allow complex and difficult data …
-
Enhancing adversarial robustness of deep neural networks
Logit-based regularization and pretrain-then-tune are two approaches that have recently been shown to enhance adversarial robustness of machine learning models. In the realm of regularization, Zhang et al. (2019) proposed TRADES, a logit-based regularization optimization function that has been …
-
Practical Diagnostic Tools for Deep Neural Networks
… of two fields: interpreting and attacking deep neural networks. Both of these goals help to improve oversight of AI. However, existing techniques are often not competitive for practical debugging in real-world applications. This thesis is dedicated to identifying and addressing gaps between …
-
Comparing learned representations of deep neural networks
In recent years, a variety of deep neural network architectures have obtained substantial accuracy improvements in tasks such as image classification, speech recognition, and machine translation, yet little is known about how different neural networks learn. To further understand this, we interpret …
-
Towards Comprehensive Visual Understanding via Deep Neural Networks
Deep neural networks (DNNs) have made significant advancements in visual scene understanding, demonstrating great potential for applications in downstream tasks such as autonomous driving, robotic navigation, and human-computer interaction. Despite these successes, generalization ability remains a …
-
Deep Neural Networks for Multi-Source Transfer Learning
Transfer learning is gaining incredible attention due to its ability to leverage previously acquired knowledge from source domain to assist in completing a task in a similar target domain. Many existing transfer learning methods deal with single source transfer learning, but rarely consider the …
Page 1 of 24