Related papers: OscNet v1.5: Energy Efficient Hopfield Network on …

Deep neural networks have become ubiquitous for applications related to visual recognition and language understanding tasks. However, it is often prohibitive to use typical neural networks on devices like mobile phones or smart watches…

Memory-augmented spiking neural networks (SNNs) promise energy-efficient neuromorphic computing, yet their generalization across sensory modalities remains unexplored. We present the first comprehensive cross-modal ablation study of memory…

Machine learning on tiny IoT devices based on microcontroller units (MCU) is appealing but challenging: the memory of microcontrollers is 2-3 orders of magnitude smaller even than mobile phones. We propose MCUNet, a framework that jointly…

Training deep learning networks involves continuous weight updates across the various layers of the deep network while using a backpropagation algorithm (BP). This results in expensive computation overheads during training. Consequently,…

Extracting features from a huge amount of data for object recognition is a challenging task. Convolution neural network can be used to meet the challenge, but it often requires a large number of computation resources. In this paper, a…

In the Internet of Things era, where we see many interconnected and heterogeneous mobile and fixed smart devices, distributing the intelligence from the cloud to the edge has become a necessity. Due to limited computational and…

The development of efficient machine learning models for molecular systems representation is becoming crucial in scientific research. We introduce TensorNet, an innovative O(3)-equivariant message-passing neural network architecture that…

Traditional artificial neural networks consist of nodes with non-oscillatory dynamics. Biological neural networks, on the other hand, consist of oscillatory components embedded in an oscillatory environment. Motivated by this feature of…

Deep convolutional neural networks (CNNs) achieve remarkable performance on image classification tasks. Recent studies, however, have demonstrated that generalization abilities are more important than the depth of neural networks for…

Integrated sensing and communication (ISAC) is a headline feature for the forthcoming IMT-2030 and 6G releases, yet a concrete solution that fits within the established orthogonal frequency division multiplexing (OFDM) family remains open.…

In this paper, we investigate learning-based MIMO-OFDM symbol detection strategies focusing on a special recurrent neural network (RNN) -- reservoir computing (RC). We first introduce the Time-Frequency RC to take advantage of the…

Oral Cavity Squamous Cell Carcinoma (OCSCC) is the most common type of head and neck cancer. Due to the subtle nature of its early stages, deep and hidden areas of development, and slow growth, OCSCC often goes undetected, leading to…

Multi-source stationary computed tomography (MSS-CT) offers significant advantages in medical and industrial applications due to its gantry-less scan architecture and/or capability of simultaneous multi-source emission. However, the lack of…

Dense optical flow estimation plays a key role in many robotic vision tasks. In the past few years, with the advent of deep learning, we have witnessed great progress in optical flow estimation. However, current networks often consist of a…

This paper introduces SpikeFit, a novel training method for Spiking Neural Networks (SNNs) that enables efficient inference on neuromorphic hardware, considering all its stringent requirements: the number of neurons and synapses that can…

We propose a systematic approach to reduce the memory consumption of deep neural network training. Specifically, we design an algorithm that costs O(sqrt(n)) memory to train a n layer network, with only the computational cost of an extra…

We introduce a fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints. ESPNet is based on a new convolutional module, efficient spatial pyramid (ESP), which is…

We present an approach to adaptively utilize deep neural networks in order to reduce the evaluation time on new examples without loss of accuracy. Rather than attempting to redesign or approximate existing networks, we propose two schemes…

Fast and reliable optimal power flow (OPF) approximation is essential for reliable smart-grid operation, yet many learning-based surrogates either flatten the native heterogeneous structure of power networks, target a limited set of grid…

Reducing inference time and energy usage while maintaining prediction accuracy has become a significant concern for deep neural networks (DNN) inference on resource-constrained edge devices. To address this problem, we propose a novel…