Related papers: OscNet: Machine Learning on CMOS Oscillator Networ…

Detecting the occlusion from stereo images or video frames is important to many computer vision applications. Previous efforts focus on bundling it with the computation of disparity or optical flow, leading to a chicken-and-egg problem. In…

The increasing amount of data to be processed on edge devices, such as cameras, has motivated Artificial Intelligence (AI) integration at the edge. Typical image processing methods performed at the edge, such as feature extraction or edge…

The rapidly increasing computational demands for artificial intelligence (AI) have spurred the exploration of computing principles beyond conventional digital computers. Physical neural networks (PNNs) offer efficient neuromorphic…

Spiking neural networks (SNNs) offer an inherent ability to process spatial-temporal data, or in other words, realworld sensory data, but suffer from the difficulty of training high accuracy models. A major thread of research on SNNs is on…

Physical reservoir computing leverages the intrinsic dynamics of mechanical systems to perform computation through their natural responses to input signals. Here, we study a compliant fiber network inspired by orb-weaving spider webs and…

We present a new type of probabilistic model which we call DISsimilarity COefficient Networks (DISCO Nets). DISCO Nets allow us to efficiently sample from a posterior distribution parametrised by a neural network. During training, DISCO…

Spiking Neural Networks (SNNs) are gaining interest due to their event-driven processing which potentially consumes low power/energy computations in hardware platforms, while offering unsupervised learning capability due to the…

Neuromorphic computing systems overcome the limitations of traditional von Neumann computing architectures. These computing systems can be further improved upon by using emerging technologies that are more efficient than CMOS for neural…

A brain--machine interface (BMI) based on motor imagery (MI) enables the control of devices using brain signals while the subject imagines performing a movement. It plays a vital role in prosthesis control and motor rehabilitation. To…

Machine-learned coarse-grained (CG) potentials are fast, but degrade over time when simulations reach under-sampled bio-molecular conformations, and generating widespread all-atom (AA) data to combat this is computationally infeasible. We…

Current AI/ML methods for data-driven engineering use models that are mostly trained offline. Such models can be expensive to build in terms of communication and computing cost, and they rely on data that is collected over extended periods…

Spiking Neural Networks (SNNs) are bio-plausible models that hold great potential for realizing energy-efficient implementations of sequential tasks on resource-constrained edge devices. However, commercial edge platforms based on standard…

Convolutional neural networks (CNN) are increasingly used in many areas of computer vision. They are particularly attractive because of their ability to "absorb" great quantities of labeled data through millions of parameters. However, as…

Our brain consists of biological neurons encoding information through accurate spike timing, yet both the architecture and learning rules of our brain remain largely unknown. Comparing to the recent development of backpropagation-based…

Optical neural networks promise ultrafast, low-energy information processing by performing computation directly with photons. Current implementations, however, are largely restricted to steady-state operation and rely on high-latency…

Hexagonal CNN models have shown superior performance in applications such as IACT data analysis and aerial scene classification due to their better rotation symmetry and reduced anisotropy. In order to realize hexagonal processing, existing…

NeuroNet is a deep convolutional neural network mimicking multiple popular and state-of-the-art brain segmentation tools including FSL, SPM, and MALPEM. The network is trained on 5,000 T1-weighted brain MRI scans from the UK Biobank Imaging…

The demand for low-power inference and training of deep neural networks (DNNs) on edge devices has intensified the need for algorithms that are both scalable and energy-efficient. While spiking neural networks (SNNs) allow for efficient…

Robotic vision introduces requirements for real-time processing of fast-varying, noisy information in a continuously changing environment. In a real-world environment, convenient assumptions, such as static camera systems and deep learning…

Previous studies have shown the great potential of capsule networks for the spatial contextual feature extraction from {hyperspectral images (HSIs)}. However, the sampling locations of the convolutional kernels of capsules are fixed and…