Related papers: HELP: Hardware-Adaptive Efficient Latency Predicti…

Deep Learning shows very good performance when trained on large labeled data sets. The problem of training a deep net on a few or one sample per class requires a different learning approach which can generalize to unseen classes using only…

Graph Neural Networks (GNNs) are becoming increasingly popular for graph-based learning tasks such as point cloud processing due to their state-of-the-art (SOTA) performance. Nevertheless, the research community has primarily focused on…

Data collected by IoT devices are often private and have a large diversity across users. Therefore, learning requires pre-training a model with available representative data samples, deploying the pre-trained model on IoT devices, and…

Event cameras detect changes in per-pixel intensity to generate asynchronous `event streams'. They offer great potential for accurate semantic map retrieval in real-time autonomous systems owing to their much higher temporal resolution and…

Large Language Models (LLMs) have emerged as a pivotal research area, yet the attention module remains a critical bottleneck in LLM inference, even with techniques like KVCache to mitigate redundant computations. While various top-$k$…

To address privacy concerns and reduce network latency, there has been a recent trend of compressing cumbersome recommendation models trained on the cloud and deploying compact recommender models to resource-limited devices for the…

Logs are a first-hand source of information for software maintenance and failure diagnosis. Log parsing, which converts semi-structured log messages into structured templates, is a prerequisite for automated log analysis tasks such as…

In recent years Deep Learning reached significant results in many practical problems, such as computer vision, natural language processing, speech recognition and many others. For many years the main goal of the research was to improve the…

The recent surge of interest surrounding Multimodal Neural Networks (MM-NN) is attributed to their ability to effectively process and integrate multiscale information from diverse data sources. MM-NNs extract and fuse features from multiple…

Model quantization is a widely used technique to compress and accelerate deep neural network (DNN) inference. Emergent DNN hardware accelerators begin to support mixed precision (1-8 bits) to further improve the computation efficiency,…

Neural Architecture Search (NAS) has emerged as a powerful framework for automatically discovering neural architectures that balance accuracy and efficiency. However, as AI transitions from static benchmarks to real-world deployment, the…

Radar sensors offer power-efficient solutions for always-on smart devices, but processing the data streams on resource-constrained embedded platforms remains challenging. This paper presents novel techniques that leverage the temporal…

Deploying federated learning across heterogeneous IoT device fleets requires tailored neural network architectures for each device class, yet existing Federated Neural Architecture Search (FedNAS) methods suffer from unguided supernet…

Neural Architecture Search (NAS) methods have been shown to outperform hand-designed models and help to democratize AI. However, NAS methods often start from scratch with each new task, making them computationally expensive and limiting…

Convolutional Neural Networks (CNNs) have become common in many fields including computer vision, speech recognition, and natural language processing. Although CNN hardware accelerators are already included as part of many SoC…

Sensor-based human activity recognition (HAR) requires to predict the action of a person based on sensor-generated time series data. HAR has attracted major interest in the past few years, thanks to the large number of applications enabled…

Designing domain specific neural networks is a time-consuming, error-prone, and expensive task. Neural Architecture Search (NAS) exists to simplify domain-specific model development but there is a gap in the literature for time series…

Graph neural networks (GNNs) have emerged as a popular strategy for handling non-Euclidean data due to their state-of-the-art performance. However, most of the current GNN model designs mainly focus on task accuracy, lacking in considering…

In this paper, we propose a learning rule based on a back-propagation (BP) algorithm that can be applied to a hardware-based deep neural network (HW-DNN) using electronic devices that exhibit discrete and limited conductance…

Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optimal performance across different inference scenarios, as they…