Related papers: Passive Batch Injection Training Technique: Boosti…
It is widely known that very small datasets produce overfitting in Deep Neural Networks (DNNs), i.e., the network becomes highly biased to the data it has been trained on. This issue is often alleviated using transfer learning,…
Modern neural network architectures have achieved remarkable accuracies but remain highly dependent on their training data, often lacking interpretability in their learned mappings. While effective on large datasets, they tend to overfit on…
Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear network will cause this negative effect. Therefore, we propose to…
Transfer learning from ImageNet is the go-to approach when applying deep learning to medical images. The approach is either to fine-tune a pre-trained model or use it as a feature extractor. Most modern architecture contain batch…
Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…
Recent research understands the residual networks from a new perspective of the implicit ensemble model. From this view, previous methods such as stochastic depth and stimulative training have further improved the performance of the…
This paper presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…
Deep learning has achieved state-of-the-art accuracies on several computer vision tasks. However, the computational and energy requirements associated with training such deep neural networks can be quite high. In this paper, we propose a…
Deep neural networks (DNNs) for supervised learning can be viewed as a pipeline of a feature extractor (i.e. last hidden layer) and a linear classifier (i.e. output layer) that is trained jointly with stochastic gradient descent (SGD). In…
Adapting large pre-trained models to unseen tasks under tight data and compute budgets remains challenging. Meta-learning approaches explicitly learn good initializations, but they require an additional meta-training phase over many tasks,…
Mixed precision training (MPT) is becoming a practical technique to improve the speed and energy efficiency of training deep neural networks by leveraging the fast hardware support for IEEE half-precision floating point that is available in…
Convolutional Neural Networks (CNNs) inherently encode strong inductive biases, enabling effective generalization on small-scale datasets. In this paper, we propose integrating this inductive bias into ViTs, not through an architectural…
Pre-training models are an important tool in Natural Language Processing (NLP), while the BERT model is a classic pre-training model whose structure has been widely adopted by followers. It was even chosen as the reference model for the…
We propose a novel approach to reduce memory consumption of the backpropagation through time (BPTT) algorithm when training recurrent neural networks (RNNs). Our approach uses dynamic programming to balance a trade-off between caching of…
Graph neural network training is mainly categorized into mini-batch and full-batch training methods. The mini-batch training method samples subgraphs from the original graph in each iteration. This sampling operation introduces extra…
The most straightforward method to accelerate Stochastic Gradient Descent (SGD) computation is to distribute the randomly selected batch of inputs over multiple processors. To keep the distributed processors fully utilized requires…
For extremely large-scale arrays (XL-arrays), the discrete Fourier transform (DFT) codebook, conventionally used in the far-field, has recently been employed for near-field beam training. However, most existing methods rely on the…
In this work, we propose to progressively increase the training difficulty during learning a neural network model via a novel strategy which we call mini-batch trimming. This strategy makes sure that the optimizer puts its focus in the…
Meta-learning has been proposed as a framework to address the challenging few-shot learning setting. The key idea is to leverage a large number of similar few-shot tasks in order to learn how to adapt a base-learner to a new task for which…
In this paper, we introduce a novel methodology for characterising the performance of deep learning networks (ResNets and DenseNet) with respect to training convergence and generalisation as a function of mini-batch size and learning rate…