LeapMind Acquires Patents for Extremely Low Bit Quantization Technology
June 23, 2021 - LeapMind Inc. (Shibuya-ku, Tokyo; CEO: Soichi Matsuda), a creator of the standard in edge AI today announced that it has been granted two patents for its extremely low bit quantization technology. “Two patents we acquired are one of the fundamental technologies supporting Efficiera, an ultra-low power AI inference accelerator IP that we developed and provided.” Commented Hiroyuki Tokunaga, CTO of LeapMind and one of the inventors of patents acquired. “We continue to develop related technologies and file patent applications.”
Patent number: No. 6885645
Date of patent registration: May 17, 2021
Title of the invention: Neural network processing units, neural network processing method, and neural network processing program, neural network processing program
Patentee: LeapMind Inc.
Patent Summary
This patent relates to a technology that minimizes the accuracy degradation associated with low bit rates, which is an issue in extremely low bit quantization technology. This is one of the methods of quantizing multi-bit data such as images, in which the multi-bit elements in the data are replaced by quantized vectors instead of simply being reduced to lower bits. In particular, the use of this technology in the input layer, which is the first stage of a deep neural network, can be highly effective.
Patent number: No. 6886747
Patent registration date: May 19, 2021
Title of the invention: Neural network processing units, neural network processing method, and neural network processing program, neural network processing program
Patentee: LeapMind Inc.
Patent Summary
The quantization operation is a comparison between the input value and the threshold value. Therefore, arbitrary monotonic functions between convolution and quantization operations can eventually be converted into threshold changes, which can be performed efficiently.
About LeapMind
LeapMind Inc. was founded in 2012 with the corporate philosophy of "bringing new devices that use machine learning to the world". Total investment in LeapMind to date has reached 4.99 billion yen (as of May 2021). The company's strength is in extremely low bit quantization for compact deep learning solutions. It has a proven track record of achievement with over 150 companies, centered in manufacturing including the automobile industry. It is also developing its Efficiera semiconductor IP, based on its experience in the development of both software and hardware.
Head office: Shibuya Dogenzaka Sky Building 5F, 28-1 Maruyama-cho, Shibuya-ku, Tokyo 150-0044
Representative: Soichi Matsuda, CEO
Established: December 2012
URL:https://leapmind.io/en/
|
Related News
- EdgeCortix Acquires Multiple Patents for Dynamic Neural Accelerator AI Processor Technology
- Sonix Introduces a New series of Extremely Low Power Consumption and High Performance 32 bit MCU powered by ARM Cortex M0 processor
- Rambus Acquires Inapac Patents
- Imec's extremely scaled SOT-MRAM devices show record low switching energy and virtually unlimited endurance
- Mosaid Acquires Major Semiconductor Process Portfolio
Breaking News
- Fractile raises $15m seed funding to develop radical new AI chip and unlock exponential performance improvements from frontier AI models
- Ceva Bluetooth Low Energy and 802.15.4 IPs Bring Ultra-Low Power Wireless Connectivity to Alif Semiconductor's Balletto Family of MCUs
- Agile Analog delivers customizable IP on GlobalFoundries' FinFet and FDX processes
- Ian Walsh appointed as Sondrel's Regional VP for America
- Systems Designed Today Must Support Post-Quantum Cryptography Tomorrow
Most Popular
- Imagination Technologies announces new capital investment from Fortress Investment Group
- Alphawave Semi: Q2 2024 Trading and Business Update
- Agile Analog delivers customizable IP on GlobalFoundries' FinFet and FDX processes
- Efinix Releases Topaz Line of FPGAs, Delivering High Performance and Low Power to Mass Market Applications
- Comcores supports BAE systems as a key partner with JESD204C IP
![]() |
E-mail This Article | ![]() |
![]() |
Printer-Friendly Page |