Related papers: SIESTA: Efficient Online Continual Learning with S…

Deep Neural Networks (DNNs) have advanced the state-of-the-art in a variety of machine learning tasks and are deployed in increasing numbers of products and services. However, the computational requirements of training and evaluating…

Continual learning is a key feature of biological neural systems, but artificial neural networks often suffer from catastrophic forgetting. Instead of backpropagation, biologically plausible learning algorithms may enable stable continual…

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns…

Spiking Neural Networks (SNNs), as an emerging biologically inspired computational model, demonstrate significant energy efficiency advantages due to their event-driven information processing mechanism. Compared to traditional Artificial…

Modern deep learning models, growing larger and more complex, have demonstrated exceptional generalization and accuracy due to training on huge datasets. This trend is expected to continue. However, the increasing size of these models poses…

Despite their success, convolutional neural networks are computationally expensive because they must examine all image locations. Stochastic attention-based models have been shown to improve computational efficiency at test time, but they…

Deep learning methods have shown outstanding performance in many applications, including single-image super-resolution (SISR). With residual connection architecture, deeply stacked convolutional neural networks provide a substantial…

Methods proposed in the literature towards continual deep learning typically operate in a task-based sequential learning setup. A sequence of tasks is learned, one at a time, with all data of current task available but not of previous or…

Inverse problems are essential to imaging applications. In this paper, we propose a model-based deep learning network, named FISTA-Net, by combining the merits of interpretability and generality of the model-based Fast Iterative…

Deep neural networks (DNNs) have achieved remarkable success in computer vision; however, training DNNs for satisfactory performance remains challenging and suffers from sensitivity to empirical selections of an optimization algorithm for…

Neural Networks (NN), although successfully applied to several Artificial Intelligence tasks, are often unnecessarily over-parametrised. In edge/fog computing, this might make their training prohibitive on resource-constrained devices,…

Recurrent neural networks (RNNs) trained using Equilibrium Propagation (EP), a biologically plausible training algorithm, have demonstrated strong performance in various tasks such as image classification and reinforcement learning.…

Deep neural networks have been shown to achieve state-of-the-art performance in several machine learning tasks. Stochastic Gradient Descent (SGD) is the preferred optimization algorithm for training these networks and asynchronous SGD…

Deep neural networks (DNNs) provide high image classification accuracy, but experience significant performance degradation when perturbation from various sources are present in the input. The lack of resilience to input perturbations makes…

Deep Neural Networks (DNNs) have revolutionized computer vision. We now have DNNs that achieve top (performance) results in many problems, including object recognition, facial expression analysis, and semantic segmentation, to name but a…

On-device Deep Neural Network (DNN) training has been recognized as crucial for privacy-preserving machine learning at the edge. However, the intensive training workload and limited onboard computing resources pose significant challenges to…

Spiking Neural Networks (SNNs) have emerged as an attractive alternative to traditional deep learning frameworks, since they provide higher computational efficiency in event driven neuromorphic hardware. However, the state-of-the-art (SOTA)…

This paper presents a new methodology to alleviate the fundamental trade-off between accuracy and latency in spiking neural networks (SNNs). The approach involves decoding confidence information over time from the SNN outputs and using it…

The success of deep neural networks (DNNs) is attributable to three factors: increased compute capacity, more complex models, and more data. These factors, however, are not always present, especially for edge applications such as autonomous…

Data quantization is an effective method to accelerate neural network training and reduce power consumption. However, it is challenging to perform low-bit quantized training: the conventional equal-precision quantization will lead to either…