Related papers: Learning from Scratch: Structurally-masked Transfo…

A machine learning (ML) design framework is proposed for adaptively adjusting clock frequency based on propagation delay of individual instructions. A random forest model is trained to classify propagation delays in real time, utilizing…

We propose a general framework to extract microscopic interactions from raw configurations with deep neural networks. The approach replaces the modeling Hamiltonian by the neural networks, in which the interaction is encoded. It can be…

Massive multiple-input multiple-output (MIMO) system is promising in providing unprecedentedly high data rate. To achieve its full potential, the transceiver needs complete channel state information (CSI) to perform transmit/receive…

Spiking neural networks (SNNs) promise orders-of-magnitude efficiency gains by communicating with sparse, event-driven spikes rather than dense numerical activations. However, most training pipelines either rely on surrogate-gradient…

Dense linear layers are a dominant source of computational and parametric cost in modern machine learning models, despite their quadratic complexity and often being misaligned with the compositional structure of learned representations. We…

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…

In our prior work, LayerPipe, we had introduced an approach to accelerate training of convolutional, fully connected, and spiking neural networks by overlapping forward and backward computation. However, despite empirical success, a…

In this work we propose for the first time a transformer-based framework for unsupervised representation learning of multivariate time series. Pre-trained models can be potentially used for downstream tasks such as regression and…

This study proposes a novel hybrid deep learning framework that integrates a Large Language Model (LLM) with a Transformer architecture for stock price forecasting. The research addresses a critical theoretical gap in existing approaches…

Accurately predicting spatio-temporal network traffic is essential for dynamically managing computing resources in modern communication systems and minimizing energy consumption. Although spatio-temporal traffic prediction has received…

Existing approaches for analyzing neural network activations, such as PCA and sparse autoencoders, rely on strong structural assumptions. Generative models offer an alternative: they can uncover structure without such assumptions and act as…

Traffic forecasting in cellular networks is a challenging spatiotemporal prediction problem due to strong temporal dependencies, spatial heterogeneity across cells, and the need for scalability to large network deployments. Traditional…

In recent years, numerous Transformer-based models have been applied to long-term time-series forecasting (LTSF) tasks. However, recent studies with linear models have questioned their effectiveness, demonstrating that simple linear layers…

As neural interfaces become more advanced, there has been an increase in the volume and complexity of neural data recordings. These interfaces capture rich information about neural dynamics that call for efficient, real-time processing…

Spiking Neural Networks (SNNs) are a promising research direction for building power-efficient information processing systems, especially for temporal tasks such as speech recognition. In SNNs, delays refer to the time needed for one spike…

In urban computing, precise and swift forecasting of multivariate time series data from traffic networks is crucial. This data incorporates additional spatial contexts such as sensor placements and road network layouts, and exhibits complex…

Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge. In time series forecasting, the autoregressive…

State-of-the-art results in large language models (LLMs) often rely on scale, which becomes computationally expensive. This has sparked a research agenda to reduce these models' parameter counts and computational costs without significantly…

Machine learning techniques using neural networks have achieved promising success for time-series data classification. However, the models that they produce are challenging to verify and interpret. In this paper, we propose an explainable…

Time delays in communication networks are one of the main concerns in deploying robots with computation boards on the edge. This article proposes a multi-stage Nonlinear Model Predictive Control (NMPC) that is capable of handling varying…