Optics.org
daily coverage of the optics & photonics industry and the markets that it serves
Featured Showcases
Photonics West Showcase
Optics+Photonics Showcase
Press Releases
Menu
Press Release

Liquid Instruments Integrates AI with Reconfigurable Test Instrumentation, Opening New Ways to Connect Machine Learning to the Physical World

Date Announced: 22 Oct 2024

SAN DIEGO and CANBERRA, Australia — Liquid Instruments, a leading innovator of reconfigurable test instrumentation, announced the integration of artificial intelligence (AI) into its Moku platform, including a brand-new instrument, the Moku Neural Network. Users can now quickly deploy machine learning (ML) models to physical systems for applications like signal analysis, denoising, sensor conditioning, closed-loop feedback, and more.

Moku harnesses the processing power of field-programmable gate arrays (FPGAs) to deliver a complete suite of instruments — from bench essentials like an oscilloscope to advanced tools like a lock-in amplifier — all on one device. Benefiting from the versatility and fast processing speed of an FPGA, plus seamless integration with other Moku instruments, the Moku Neural Network enables users to rapidly develop and train their own artificial neural networks with Python and upload them to their Moku:Pro device.

“The Moku Neural Network is designed to enable scientists and engineers to easily integrate machine learning into their experiments,” said Daniel Shaddock, co-founder and CEO of Liquid Instruments. “Moku has always offered flexible and easy-to-use tools for advanced R&D. This latest release demonstrates the platform’s extensibility, adding new AI/ML capabilities through a software update.”

The Moku Neural Network has an architecture that includes input, hidden, and output layers, as well as customizable activation functions. With sub-microsecond latency, up to five fully connected layers of up to 100 neurons each, and customizable activation functions, it accommodates a range of applications. Users can analyze up to four input channels in parallel mode, or process time series data in serial mode, with up to four outputs for processing experimental data — all in real time.

To help users quickly unlock the full potential of Moku devices, Liquid Instruments is also introducing AI Help, a GenAI tool that provides fast answers to product questions. This tool makes it easier than ever to explore and maximize the capabilities of Moku. As with many GenAI tools, it is expected to evolve, improve, and expand over time.

Liquid Instruments aims to empower users with a reconfigurable suite of versatile, easy-to-use test instruments. With regular software updates, plus machine learning capabilities and the ability to integrate with new technologies, the Moku platform is designed to grow with users over time, redefining the cost and effort to move from idea to implementation in advanced research and development applications.

Contact


Contact Liquid Instruments at media@liquidinstruments.com.

E-mail: matt.mcardle@liquidinstruments.com

Web Site: https://www.liquidinstruments.com/

© 2024 SPIE Europe
Top of Page