Related papers: Flattening Sharpness for Dynamic Gradient Projecti…
Error backpropagation is a highly effective mechanism for learning high-quality hierarchical features in deep networks. Updating the features or weights in one layer, however, requires waiting for the propagation of error signals from…
Training the deep convolutional neural network for computer vision problems is slow and inefficient, especially when it is large and distributed across multiple devices. The inefficiency is caused by the backpropagation algorithm's forward…
Questions remain on the robustness of data-driven learning methods when crossing the gap from simulation to reality. We utilize weight anchoring, a method known from continual learning, to cultivate and fixate desired behavior in Neural…
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification. In this method, subsequent tasks are trained using the inactive neurons and…
We conjecture that the inherent difference in generalisation between adaptive and non-adaptive gradient methods in deep learning stems from the increased estimation noise in the flattest directions of the true loss surface. We demonstrate…
Catastrophic forgetting is a critical challenge in training deep neural networks. Although continual learning has been investigated as a countermeasure to the problem, it often suffers from the requirements of additional network components…
Forward gradient learning computes a noisy directional gradient and is a biologically plausible alternative to backprop for learning deep neural networks. However, the standard forward gradient algorithm, when applied naively, suffers from…
The problem of a deep learning model losing performance on a previously learned task when fine-tuned to a new one is a phenomenon known as Catastrophic forgetting. There are two major ways to mitigate this problem: either preserving…
Sharpness-Aware Minimization (SAM) has recently emerged as an effective technique for improving DNN robustness to input variations. However, its interplay with the compactness requirements of on-device DNN deployments remains less explored.…
Catastrophic forgetting refers to the tendency that a neural network "forgets" the previous learned knowledge upon learning new tasks. Prior methods have been focused on overcoming this problem on convolutional neural networks (CNNs), where…
Classical analyses of gradient descent (GD) define a stability threshold based on the largest eigenvalue of the loss Hessian, often termed sharpness. When the learning rate lies below this threshold, training is stable and the loss…
Deep neural networks (DNNs) are becoming increasingly deeper, wider, and non-linear due to the growing demands on prediction accuracy and analysis quality. When training a DNN model, the intermediate activation data must be saved in the…
Existing research on task incremental learning in continual learning has primarily focused on preventing catastrophic forgetting (CF). Although several techniques have achieved learning with no CF, they attain it by letting each task…
Contrastive learning has significantly improved representation quality, enhancing knowledge transfer across tasks in continual learning (CL). However, catastrophic forgetting remains a key challenge, as contrastive based methods primarily…
The massive interest in deep neural networks (DNNs) for both computer vision and natural language processing has been sparked by the growth in computational power. However, this led to an increase in the memory footprint, to a point where…
An important class of problems involves training deep neural networks with sparse prediction targets of very high dimension D. These occur naturally in e.g. neural language models or the learning of word-embeddings, often posed as…
The rapid increase in the parameters of deep learning models has led to significant costs, challenging computational efficiency and model interpretability. In this paper, we introduce a novel and straightforward neural network pruning…
The fast adaptation capability of deep neural networks in non-stationary environments is critical for online time series forecasting. Successful solutions require handling changes to new and recurring patterns. However, training deep neural…
We report, for the first time, on the cascade weight shedding phenomenon in deep neural networks where in response to pruning a small percentage of a network's weights, a large percentage of the remaining is shed over a few epochs during…
Continual learning remains challenging due to catastrophic forgetting, where neural networks lose previously acquired knowledge when learning new tasks. Inspired by memory consolidation in neuroscience, we propose FSC-Net (Fast-Slow…