Related papers: OscNet v1.5: Energy Efficient Hopfield Network on …
Recent years have witnessed the success of deep networks in compressed sensing (CS), which allows for a significant reduction in sampling cost and has gained growing attention since its inception. In this paper, we propose a new practical…
In-memory computing is a promising non-von Neumann approach for making energy-efficient deep learning inference hardware. Crossbar arrays of resistive memory devices can be used to encode the network weights and perform efficient analog…
An important difference between brains and deep neural networks is the way they learn. Nervous systems learn online where a stream of noisy data points are presented in a non-independent, identically distributed (non-i.i.d.) way. Further,…
Optical neural networks (ONNs) have demonstrated record-breaking potential in high-performance neuromorphic computing due to their ultra-high execution speed and low energy consumption. However, current learning protocols fail to provide…
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…
Distributed learning is widely used for training large models on large datasets by distributing parts of the model or dataset across multiple devices and aggregating the computed results for subsequent computations or parameter updates.…
Dynamic networks have shown their promising capability in reducing theoretical computation complexity by adapting their architectures to the input during inference. However, their practical runtime usually lags behind the theoretical…
We propose a novel deep learning model named ACLNet, for cloud segmentation from ground images. ACLNet uses both deep neural network and machine learning (ML) algorithm to extract complementary features. Specifically, it uses…
A recurrent artificial neural network known as Hopfield network is used for pattern storage. Here we have applied this associative memory type network for pattern recognition for predictive controls and diagnostics in accelerator based…
One of the most computationally intensive parts in modern recognition systems is an inference of deep neural networks that are used for image classification, segmentation, enhancement, and recognition. The growing popularity of edge…
In this work we introduce impostor networks, an architecture that allows to perform fine-grained recognition with high accuracy and using a light-weight convolutional network, making it particularly suitable for fine-grained applications on…
Deep neural networks (DNNs) are reshaping the field of information processing. With their exponential growth challenging existing electronic hardware, optical neural networks (ONNs) are emerging to process DNN tasks in the optical domain…
Semantic segmentation is a fundamental task in visual scene understanding. We focus on the supervised setting, where ground-truth semantic annotations are available. Based on knowledge about the high regularity of real-world scenes, we…
Efficient machine learning deployment requires models that account for hardware constraints. Because binary logic gates are the fundamental primitives of digital hardware, models built directly from logic operations offer a promising path…
Depth estimation from light field (LF) images is a fundamental step for numerous applications. Recently, learning-based methods have achieved higher accuracy and efficiency than the traditional methods. However, it is costly to obtain…
In this work, we propose a low-bit training framework for convolutional neural networks, which is built around a novel multi-level scaling (MLS) tensor format. Our framework focuses on reducing the energy consumption of convolution…
We propose a novel, brain-inspired deep neural network model known as the Deep Oscillatory Neural Network (DONN). Deep neural networks like the Recurrent Neural Networks indeed possess sequence processing capabilities but the internal…
We propose a novel deep learning framework based on Vision Transformers (ViT) for one-class classification. The core idea is to use zero-centered Gaussian noise as a pseudo-negative class for latent space representation and then train the…
We present a simple and quick method to approximate network centrality indexes. Our approach, called QuickCent, is inspired by so-called fast and frugal heuristics, which are heuristics initially proposed to model some human decision and…
This work targets the automated minimum-energy optimization of Quantized Neural Networks (QNNs) - networks using low precision weights and activations. These networks are trained from scratch at an arbitrary fixed point precision. At…