Revolutionizing the EDA industry using machine learning

February 2, 2018 Anupam Bakshi, Agnisys

Machine learning (ML) is the rage these days and we at Agnisys were not untouched by it. Being immersed in specifications and dealing with customer queries about register and sequence specification on a daily basis, we thought, why not help the customer using ML? So we decided to use these ML algorithms.

The task of using ML was interesting but challenging. We deal with hardware specifications which are usually written in English. There is also heavy use of semiconductor and electronics industry jargons. We had to use NLP (Natural Language Processing) libraries for parsing and tokenizing the text after much pre-processing. There are several libraries for ML already in place.

We chose the TensorFlow library because that is becoming the de facto standard. Having incorporated the ML algorithms in IDesignSpec, we are looking for even wider application in all our products. It has been an enlightening experience for us. It is surprising that the ML industry is already so mature and advanced.

We feel that we are late to the ML party, but I think we are early in terms of EDA industry adopting ML in a big way. Agnisys is making headway with home-grown machine-learning algorithms — and applying it to IDS NextGen multi-platform product, which helps user to create SoC specification at an enterprise level.

Anupam Bakshi is the founder and CEO at Agnisys. He has more than two decades of experience implementing a wide range of products and services in the High-Tech industry. Prior to forming Agnisys, he held various management and technical lead roles at companies such as Avid Technology Inc., PictureTel Corporation, Blackstone Consulting Group, Cadence Design Systems and Gateway Design Automation. Anupam has earned a High-tech MBA from Northeastern University, Massachusetts, a Master’s in Computer Engineering also from Northeastern University and a Masters in Science (Electronics) from Delhi University.

Previous Article
SEGGER Embedded Studio supports RISC-V architecture
SEGGER Embedded Studio supports RISC-V architecture

RISC-V edition of Embedded Studio IDE released.

Next Article
dbForge SQL Complete v5.8 update provides new productivity features

Context-based T-SQL prompts that will speed up SQL code writing and improve its accuracy and readability we...