Related papers: Can we learn better with hard samples?
In this paper, we describe a phenomenon, which we named "super-convergence", where neural networks can be trained an order of magnitude faster than with standard training methods. The existence of super-convergence is relevant to…
The remarkable successes of deep learning models across various applications have resulted in the design of deeper networks that can solve complex problems. However, the increasing depth of such models also results in a higher storage and…
For fast and energy-efficient deployment of trained deep neural networks on resource-constrained embedded hardware, each learned weight parameter should ideally be represented and stored using a single bit. Error-rates usually increase when…
Deep neural networks may perform poorly when training datasets are heavily class-imbalanced. Recently, two-stage methods decouple representation learning and classifier learning to improve performance. But there is still the vital issue of…
Despite its astounding success in learning deeper multi-dimensional data, the performance of deep learning declines on new unseen tasks mainly due to its focus on same-distribution prediction. Moreover, deep learning is notorious for poor…
Memory is increasingly often the bottleneck when training neural network models. Despite this, techniques to lower the overall memory requirements of training have been less widely studied compared to the extensive literature on reducing…
Can we modify the training data distribution to encourage the underlying optimization method toward finding solutions with superior generalization performance on in-distribution data? In this work, we approach this question for the first…
Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in longer training times that impede research and development progress. Distributed synchronous SGD offers a potential…
This paper presents a comparative analysis of distributed training strategies for large-scale neural networks, focusing on data parallelism, model parallelism, and hybrid approaches. We evaluate these strategies on image classification…
Supervised deep learning requires a large amount of training samples with annotations (e.g. label class for classification task, pixel- or voxel-wised label map for segmentation tasks), which are expensive and time-consuming to obtain.…
Few-shot learning is the process of learning novel classes using only a few examples and it remains a challenging task in machine learning. Many sophisticated few-shot learning algorithms have been proposed based on the notion that networks…
Deep Neural Networks (DNNs) are inherently computation-intensive and also power-hungry. Hardware accelerators such as Field Programmable Gate Arrays (FPGAs) are a promising solution that can satisfy these requirements for both embedded and…
Artificial Intelligence algorithms have been steadily increasing in popularity and usage. Deep Learning, allows neural networks to be trained using huge datasets and also removes the need for human extracted features, as it automates the…
Recently published methods enable training of bitwise neural networks which allow reduced representation of down to a single bit per weight. We present a method that exploits ensemble decisions based on multiple stochastically sampled…
Machine learning, especially deep neural networks, has been rapidly developed in fields including computer vision, speech recognition and reinforcement learning. Although Mini-batch SGD is one of the most popular stochastic optimization…
Importance sampling has been successfully used to accelerate stochastic optimization in many convex problems. However, the lack of an efficient way to calculate the importance still hinders its application to Deep Learning. In this paper,…
Background: Deep learning models are typically trained using stochastic gradient descent or one of its variants. These methods update the weights using their gradient, estimated from a small fraction of the training data. It has been…
ResNets (or Residual Networks) are one of the most commonly used models for image classification tasks. In this project, we design and train a modified ResNet model for CIFAR-10 image classification. In particular, we aimed at maximizing…
Mini-batch stochastic gradient methods (SGD) are state of the art for distributed training of deep neural networks. Drastic increases in the mini-batch sizes have lead to key efficiency and scalability gains in recent years. However,…
Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…