Alex Yakovlev

A Real-Time Tsetlin Machine-based Non-intrusive Load Monitoring System on MCUs

Han Wu, Tianhang Tan, Shengyu Duan, Alex Yakovlev et autres

Non-Intrusive Load Monitoring (NILM) systems estimate individual appliance energy consumption from a single aggregate meter, without requiring separate sensors for each device. By installing a single meter that measures a building's total electricity consumption, NILM algorithms can determine the active status of …

Wave‐Based Quasi‐digital Logic Operations

Ross Glyn MacDonald, Alex Yakovlev, Víctor Pacheco‐Peña

Electromagnetic (EM) wave‐based computing has emerged as an exciting paradigm with the potential to enable high‐speed, parallel operations. In conventional computing, elementary logic gates, such as AND , OR , NOT , and XOR , form the building blocks of larger interconnected …

gb (code pays fourni par la source)

Laser-Based Raindrop Sensing and 2-D Ultrasonic Wind Measurement for Wind-Induced Bias Correction in Rainfall

Mark Dutton, Enda O’Connell, Alex Yakovlev, Domenico Balsamo

gb (code pays fourni par la source)

Distributed Places and Safe Net Reduction

Victor Khomenko, Maciej Koutny, Alex Yakovlev

Being able to find small Petri nets with the same behaviour as formal specifications of concurrent systems benefits both effective verification and practical implementation of such systems. This paper considers specifications given in the form of compositionally defined safe nets. The paper …

LatentGraph: From Latent States to Rule-based Expressions for Explainable Financial Forecasting

Ekin Can Erkuş, Alex Chan, Walter Distaso, David B. Thomas et autres

Financial risk management needs forecasting tools that explain their reasoning, since accuracy alone is insufficient for board decisions. Accordingly, the advancement of classification models demands end-to-end transparency for the decisions they make. To address this, this paper presents LatentGraph, which aims for …

gb (code pays fourni par la source)

Event-Driven Digital-Time-Domain Inference Architectures for Tsetlin Machines

Tian Lan, Rishad Shafik, Alex Yakovlev

Machine learning fits model parameters to approximate input-output mappings, predicting unknown samples. However, these models often require extensive arithmetic computations during inference, increasing latency and power consumption. This paper proposes a digital-time-domain computing approach for Tsetlin machine (TM) inference process to address …

Flexibility Extension of the Event Picking Service for the ATLAS Experiment

E. Alexandrov, I. N. Aleksandrov, D. Barberis, Alex Yakovlev

Abstract The ATLAS EventIndex is a catalog of all recorded and simulated ATLAS events, one of four main experiments at the LHC accelerator at CERN. The Event Picking Service is one of the components of the ATLAS Event Index. It is used …

ru, it (code pays fourni par la source)

Production of the Configuration Information System for the BM@N Experiment

E. Alexandrov, I. N. Aleksandrov, A. Chebotov, I. Filozova et autres

Abstract The collection, storage and processing of experimental data are an integral part of modern high-energy physics experiments. The Configuration Information System (CIS) is an essential element of a complex of information systems developed for particle collision experiments. The CIS has been …

ru (code pays fourni par la source)

A Tsetlin Machine Image Classification Accelerator on a Flexible Substrate

Marcos L. L. Sartori, Shengyu Duan, Emre Özer, Rishad Shafik et autres

This paper introduces the first implementation of digital Tsetlin Machines (TMs) on flexible integrated circuit (FlexIC) using Pragmatic's 600nm IGZO-based FlexIC technology. TMs, known for their energy efficiency, interpretability, and suitability for edge computing, have previously been limited by the rigidity of …

Fast and Compact Tsetlin Machine Inference on CPUs Using Instruction-Level Optimization

Shengyu Duan, Rishad Shafik, Alex Yakovlev

The Tsetlin Machine (TM) offers high-speed inference on resource-constrained devices such as CPUs. Its logic-driven operations naturally lend themselves to parallel execution on modern CPU architectures. Motivated by this, we propose an efficient software implementation of the TM by leveraging instruction-level bitwise …

Topological Valley Photonic Waveguides: Scattering Matrix Evaluation for Linear Computing

Christian Johnson-Richards, Alex Yakovlev, Víctor Pacheco‐Peña

Topological boundary modes utilizing valley mode waveguides have opened opportunities in, for instance, the design of high transmission waveguides with tolerance to geometrical defects and sharp bends. Applications of these waveguides include linear computational processes and the emulation of logic gates using …

gb (code pays fourni par la source)

Electromagnetic wave-based quasi-digital linear logic operations

R G. MacDonald, Alex Yakovlev, Víctor Pacheco‐Peña

In this work, the constructive and destructive interference of electromagnetic (EM) waves will be exploited to implement quasi-digital logic operations. Different than true digital operations, these quasi-digital operations are implemented using entirely linear structures by carefully tailoring the encoding scheme of the …

gb (code pays fourni par la source)