Related papers: Optimizing TinyML: The Impact of Reduced Data Acqu…

We propose two optimization techniques to minimize memory usage and computation while meeting system timing constraints for real-time classification in wearable systems. Our method derives a hierarchical classifier structure for Support…

This research aims to optimize intricate learning models by implementing quantization and bit-depth optimization techniques. The objective is to significantly cut time complexity while preserving model efficiency, thus addressing the…

Limited computational budgets often prevent transformers from being used in production and from having their high accuracy utilized. TinyBERT addresses the computational efficiency by self-distilling BERT into a smaller transformer…

Mining machinery operating in variable environments faces high wear and unpredictable stress, challenging Predictive Maintenance (PdM). This paper introduces the Edge Sensor Network for Predictive Maintenance (ESN-PdM), a hierarchical…

The growing demand for low-power and area-efficient TinyML inference on AIoT devices necessitates memory architectures that minimise data movement while sustaining high computational efficiency. This paper presents FERMI-ML, a Flexible and…

Optimization of radio hardware and AI-based network management software yield significant energy savings in radio access networks. The execution of underlying Machine Learning (ML) models, which enable energy savings through recommended…

Recent advances in deep reinforcement learning (DRL) have largely promoted the performance of adaptive traffic signal control (ATSC). Nevertheless, regarding the implementation, most works are cumbersome in terms of storage and computation.…

The increasing deployment of large language models (LLMs) in natural language processing (NLP) tasks raises concerns about energy efficiency and sustainability. While prior research has largely focused on energy consumption during model…

Model-predictive control (MPC) is a powerful tool for controlling highly dynamic robotic systems subject to complex constraints. However, MPC is computationally demanding, and is often impractical to implement on small, resource-constrained…

IoT devices based on microcontroller units (MCU) provide ultra-low power consumption and ubiquitous computation for near-sensor deep learning models (DNN). However, the memory of MCU is usually 2-3 orders of magnitude smaller than mobile…

The Tsetlin Machine (TM) is a novel alternative to deep neural networks (DNNs). Unlike DNNs, which rely on multi-path arithmetic operations, a TM learns propositional logic patterns from data literals using Tsetlin automata. This…

The demand to process vast amounts of data generated from state-of-the-art high resolution cameras has motivated novel energy-efficient on-device AI solutions. Visual data in such cameras are usually captured in the form of analog voltages…

Accurate time-series predictions in machine learning are heavily influenced by the selection of appropriate input time length and sampling rate. This paper introduces ATLO-ML, an adaptive time-length optimization system that automatically…

Over the past decade, the dominance of deep learning has prevailed across various domains of artificial intelligence, including natural language processing, computer vision, and biomedical signal processing. While there have been remarkable…

Along with the progress of AI democratization, machine learning (ML) has been successfully applied to edge applications, such as smart phones and automated driving. Nowadays, more applications require ML on tiny devices with extremely…

Time-series data processing is an important component of many real-world applications, such as health monitoring, environmental monitoring, and digital agriculture. These applications collect distinct windows of sensor data (e.g., few…

Machine learning (ML) has become a pervasive tool across computing systems. An emerging application that stress-tests the challenges of ML system design is tiny robot learning, the deployment of ML on resource-constrained low-cost…

The growing demands of processing massive datasets have promoted irresistible trends of running machine learning applications on MapReduce. When processing large input data, it is often of greater values to produce fast and accurate enough…

Machine learning models benefit when allowed to learn from temporal trends in time-stamped administrative data. These trends can be represented by dividing a model's observation window into time segments or bins. Model training time and…

Accurate quantum state readout is crucial for error correction and algorithms, but measurement errors are detrimental. Readout fidelity is typically limited by a poor signal-to-noise ratio (SNR) and energy relaxation ($T_1$ decay), a…