Related papers: VLSI Extreme Learning Machine: A Design Space Expl…

The incorporation of high-performance optoelectronic devices into photonic neuromorphic processors can substantially accelerate computationally intensive operations in machine learning (ML) algorithms. However, the conventional device…

Most video-and-language representation learning approaches employ contrastive learning, e.g., CLIP, to project the video and text features into a common latent space according to the semantic similarities of text-video pairs. However, such…

This paper introduces EdgeProfiler, a fast profiling framework designed for evaluating lightweight Large Language Models (LLMs) on edge systems. While LLMs offer remarkable capabilities in natural language understanding and generation,…

On-device intelligence is gaining significant attention recently as it offers local data processing and low power consumption. In this research, an on-device training circuitry for threshold-current memristors integrated in a crossbar…

Due to the nonlinear distortion in Orthogonal frequency division multiplexing (OFDM) systems, the timing synchronization (TS) performance is inevitably degraded at the receiver. To relieve this issue, an extreme learning machine (ELM)-based…

Multiple-input multiple-output orthogonal frequency-division multiplexing (MIMO-OFDM) is a key technology component in the evolution towards cognitive radio (CR) in next-generation communication in which the accuracy of timing and frequency…

Instance segmentation in electron microscopy (EM) volumes is tough due to complex shapes and sparse annotations. Self-supervised learning helps but still struggles with intricate visual patterns in EM. To address this, we propose a…

It is often desirable to be able to recognize when inputs to a recognition function learned in a supervised manner correspond to classes unseen at training time. With this ability, new class labels could be assigned to these inputs by a…

Reinforcement learning (RL) has become a key training step for improving mathematical reasoning in large language models (LLMs), but it often has high GPU memory usage, which makes it hard to use in settings with limited resources. To…

In frequency-division duplexing (FDD) massive multiple-input multiple-output (MIMO), deep learning (DL)-based superimposed channel state information (CSI) feedback has presented promising performance. However, it is still facing many…

Optical architectures have been emerging as an energy-efficient and high-throughput hardware platform to accelerate computationally intensive general matrix-matrix multiplications (GEMMs) in modern machine learning (ML) algorithms. However,…

Printed electronics (PE) promises on-demand fabrication, low non-recurring engineering costs, and sub-cent fabrication costs. It also allows for high customization that would be infeasible in silicon, and bespoke architectures prevail to…

The inverse-free extreme learning machine (ELM) algorithm proposed in [4] was based on an inverse-free algorithm to compute the regularized pseudo-inverse, which was deduced from an inverse-free recursive algorithm to update the inverse of…

We show that the mutual information between the representation of a learning machine and the hidden features that it extracts from data is bounded from below by the relevance, which is the entropy of the model's energy distribution. Models…

General matrix multiplication (GEMM) is a fundamental operation in deep learning (DL). With DL moving increasingly toward low precision, recent works have proposed novel unary GEMM designs as an alternative to conventional binary GEMM…

Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory…

One-class classification (OCC) needs samples from only a single class to train the classifier. Recently, an auto-associative kernel extreme learning machine was developed for the OCC task. This paper introduces a novel extension of this…

In order to constrain ultra light dark matter models with current and near future weak lensing surveys we need the predictions for the non-linear dark matter power-spectrum. This is commonly extracted from numerical simulations or from…

High-order tensor decomposition has been widely adopted to obtain compact deep neural networks for edge deployment. However, existing studies focus primarily on its algorithmic advantages such as accuracy and compression ratio-while…

We study the problem of learning similarity by using nonlinear embedding models (e.g., neural networks) from all possible pairs. This problem is well-known for its difficulty of training with the extreme number of pairs. For the special…