Related papers: Efficiency Evaluation of Character-level RNN Train…

Fault-aware retraining has emerged as a prominent technique for mitigating permanent faults in Deep Neural Network (DNN) hardware accelerators. However, retraining leads to huge overheads, specifically when used for fine-tuning large DNNs…

Recurrent Neural networks (RNN) have shown promising potential for learning dynamics of sequential data. However, artificial neural networks are known to exhibit poor robustness in presence of input noise, where the sequential architecture…

When applied to high-dimensional datasets, feature selection algorithms might still leave dozens of irrelevant variables in the dataset. Therefore, even after feature selection has been applied, classifiers must be prepared to the presence…

Deep neural networks (DNNs) depend on the storage of a large number of parameters, which consumes an important portion of the energy used during inference. This paper considers the case where the energy usage of memory elements can be…

A key attribute that drives the unprecedented success of modern Recurrent Neural Networks (RNNs) on learning tasks which involve sequential data, is their ability to model intricate long-term temporal dependencies. However, a well…

Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other…

Recurrent neural networks (RNNs) are powerful constructs capable of modeling complex systems, up to and including Turing Machines. However, learning such complex models from finite training sets can be difficult. In this paper we…

Convolutional neural networks (CNNs) have been increasingly deployed to edge devices. Hence, many efforts have been made towards efficient CNN inference in resource-constrained platforms. This paper attempts to explore an orthogonal…

Deep convolutional neural networks have achieved great success in various applications. However, training an effective DNN model for a specific task is rather challenging because it requires a prior knowledge or experience to design the…

Training neural networks is traditionally done by providing a sequence of random mini-batches sampled uniformly from the entire training data. In this work, we analyze the effect of curriculum learning, which involves the non-uniform…

GPUs have been favored for training deep learning models due to their highly parallelized architecture. As a result, most studies on training optimization focus on GPUs. There is often a trade-off, however, between cost and efficiency when…

Among attempts at giving a theoretical account of the success of deep neural networks, a recent line of work has identified a so-called lazy training regime in which the network can be well approximated by its linearization around…

A curriculum is a planned sequence of learning materials and an effective one can make learning efficient and effective for both humans and machines. Recent studies developed effective data-driven curriculum learning approaches for training…

Deep residual networks (ResNets) and their variants are widely used in many computer vision applications and natural language processing tasks. However, the theoretical principles for designing and training ResNets are still not fully…

Deep recurrent neural networks perform well on sequence data and are the model of choice. However, it is a daunting task to decide the structure of the networks, i.e. the number of layers, especially considering different computational…

Recurrent Neural Networks (RNNs) are powerful tools for solving sequence-based problems, but their efficacy and execution time are dependent on the size of the network. Following recent work in simplifying these networks with model pruning…

Human motion modelling is a classical problem at the intersection of graphics and computer vision, with applications spanning human-computer interaction, motion synthesis, and motion prediction for virtual and augmented reality. Following…

In business retention, churn prevention has always been a major concern. This work contributes to this domain by formalizing the problem of churn prediction in the context of online gambling as a binary classification task. We also propose…

Research on adversarial robustness in language models is currently fragmented across applications and attacks, obscuring shared vulnerabilities. In this work, we propose unifying the study of adversarial robustness in text scoring models…

We study the design of computationally efficient algorithms with provable guarantees, that are robust to adversarial (test time) perturbations. While there has been an proliferation of recent work on this topic due to its connections to…