Boot Camp – Machine Learning & Artificial Intelligence for Hardware & Electronics Design

Tue. January 29| 9:00 AM - 4:30 PM | Great America 2

Pass Type: Boot Camp Pass

Track: 15. Machine Learning for Microelectronics, Signaling & System Design

Audience Level: All

Session Type: Boot Camp

Description:

A day long introduction for beginners who are interested in learning the basics of machine learning (ML) and artificial intelligence (AI) and their applications in hardware and electronics design. Participants will have hands-on opportunity to measure and train dynamic neural networks to illustrate its usefulness for complex equalizer modelling.

Please note: In order to take part in the hands-on instruction during this boot camp, you must bring your laptop and have TensorFlow and Keras software loaded and running.

Before the boot camp, go to the sites below and follow the instructions:

  • Download and install TensorFlow here
  • Download and install Keras here


Topics covered:

Introduction
We will start the day with a brief introduction to generative vs. discriminative models and their differences. From these models, we can consider examples where deploying machine learning/AI techniques can have big advantages and cases where they may not help.

Linear & logistic regression
This session introduces the basic concepts of linear and logistic regression in multidimensional spaces. It includes the mapping concept, and mentions regularized regression to address over-fitting. Participants will begin to learn how to use collection of input and output samples to implement generative models. Session ends with research examples applying regularized regression for nonlinear functions.

Machine learning for design optimization
The tutorial will cover the basics of machine learning based design optimization. Participants will learn how to use readily available tools and algorithms which can be integrated with their current simulation framework.

Artificial neural networks, regularization & gradient descent
We will move into the area of artificial neural networks. This is one of the most popular artificial intelligence engine. Concepts of input, output and hidden layer will be discussed. Activation functions and the overall operation of the ANN will also be discussed. Method to converge to optimal solutions for ANN through back propagation and gradient descent will be discussed. Undesirable results such as over/under fitting and their mitigation through regularization will be covered.

Bayesian surrogate models
Participants will be introduced to the important concept of Bayesian surrogate models to effectively model analog generative models

Recurrent neural networks
More advance neural network structures such as recurrent neural network will be discussed including their application in time series analysis for SI.

Advance topics in machine learning and AI (PCA and self-correcting models)
We will briefly touch on some advance topics and their application in hardware design. Examples will be using Principal component analysis for channel performance optimization, causal and structural inference for complex deep state space models such as hidden Markov and recurrent neural networks

Live demo of using test instruments as machine learning tools
The course will end with a hands on demo of using recurrent neural network to create a complex equalizing receiver model with test instruments. Measurements results will be compared with original IBIS-AMI models, any mismatch will be corrected through retraining of the recurrent neural network model (i.e. self-correcting model) without needing to know the IBIS or the receiver IP. Participants should bring their own Windows based laptop to run the program.




Takeaway:


Speakers

Christopher Cheng

Christopher Cheng

Distinguished Technologist

Hewlett Packard Enterprise

Role: Speaker

Paul Franzon

Paul Franzon

Cirrus Logic Distinguished Professor

North Carolina State University

Role: Speaker

Madhavan Swaminathan

Madhavan Swaminathan

John Pippin Chair Professor

Georgia Institute of Technology

Role: Speaker

YongJin Choi

YongJin Choi

Master Technologist

HP Enterprise

Role: Speaker

Ting Zhu

Ting Zhu

Expert Engineer

HP Enterprise

Role: Speaker

Seamus Brokaw

Seamus Brokaw

Software Engineer

Tektronix

Role: Speaker

Majid Ahadi Dolatsara

Majid Ahadi Dolatsara

Ph.D. Student

Georgia Institute of Technology, Atlanta

Role: Speaker

Huan Yu

Huan Yu

Ph.D. Student

Georgia Institute of Technology

Role: Speaker

Hakki Mert Torun

Hakki Mert Torun

Ph.D. Student

Georgia Institute of Technology

Role: Speaker