相关论文: Advancing On-Device Neural Network Training with T…

Current deep learning (DL) systems rely on a centralized computing paradigm which limits the amount of available training data, increases system latency, and adds privacy and security constraints. On-device learning, enabled by…

Pruning of deep neural networks has been an effective technique for reducing model size while preserving most of the performance of dense networks, crucial for deploying models on memory and power-constrained devices. While recent sparse…

Diffusion Policies have significantly advanced robotic manipulation tasks via imitation learning, but their application on resource-constrained mobile platforms remains challenging due to computational inefficiency and extensive memory…

We propose a novel adaptive empirical Bayesian method for sparse deep learning, where the sparsity is ensured via a class of self-adaptive spike-and-slab priors. The proposed method works by alternatively sampling from an adaptive…

With increasing scale in model and dataset size, the training of deep neural networks becomes a massive computational burden. One approach to speed up the training process is Selective Backprop. For this approach, we perform a forward pass…

End-to-end multi-modal planning has been widely adopted to model the uncertainty of driving behavior, typically by scoring candidate trajectories and selecting the optimal one. Existing approaches generally fall into two categories: scoring…

The training of sparse neural networks is becoming an increasingly important tool for reducing the computational footprint of models at training and evaluation, as well enabling the effective scaling up of models. Whereas much work over the…

Robustness and compactness are two essential attributes of deep learning models that are deployed in the real world. The goals of robustness and compactness may seem to be at odds, since robustness requires generalization across domains,…

Phenomenally successful in practical inference problems, convolutional neural networks (CNN) are widely deployed in mobile devices, data centers, and even supercomputers. The number of parameters needed in CNNs, however, are often large and…

Arguably the biggest challenge in applying neural networks is tuning the hyperparameters, in particular the learning rate. The sensitivity to the learning rate is due to the reliance on backpropagation to train the network. In this paper we…

Human Activity Recognition (HAR) on resource constrained wearables requires models that balance accuracy against strict memory and computational budgets. State of the art lightweight architectures such as TinierHAR (34K parameters) and…

Deep neural networks have achieved remarkable success across a range of tasks, however their computational demands often make them unsuitable for deployment on resource-constrained edge devices. This paper explores strategies for…

The ever-growing computational demands of increasingly complex machine learning models frequently necessitate the use of powerful cloud-based infrastructure for their training. Binary neural networks are known to be promising candidates for…

Modern deep networks have millions to billions of parameters, which leads to high memory and energy requirements during training as well as during inference on resource-constrained edge devices. Consequently, pruning techniques have been…

Sparsity is a well-studied technique for compressing deep neural networks (DNNs) without compromising performance. In deep reinforcement learning (DRL), neural networks with up to 5% of their original weights can still be trained with…

Reversible Spiking Neural Networks (RevSNNs) enable memory-efficient training by reconstructing forward activations during backpropagation, but suffer from high latency due to strictly sequential computation. To overcome this limitation, we…

Automated feature extraction capability and significant performance of Deep Neural Networks (DNN) make them suitable for Internet of Things (IoT) applications. However, deploying DNN on edge devices becomes prohibitive due to the colossal…

Spiking Neural Networks (SNNs) are more biologically plausible and computationally efficient. Therefore, SNNs have the natural advantage of drawing the sparse structural plasticity of brain development to alleviate the energy problems of…

Learn in-situ is a growing trend for Edge AI. Training deep neural network (DNN) on edge devices is challenging because both energy and memory are constrained. Low precision training helps to reduce the energy cost of a single training…

Spiking Neural Networks (SNNs) are emerging as a brain-inspired alternative to traditional Artificial Neural Networks (ANNs), prized for their potential energy efficiency on neuromorphic hardware. Despite this, SNNs often suffer from…