2018 International Conference On Computer Aided Design

The Premier Conference Devoted to Technical Innovations in Electronic Design Automation

November 5-8, 2018Hilton San Diego Resort & Spa San Diego, CA

MP Associates, Inc.

THURSDAY November 08, 8:00am - 12:00pm | Monte Carlo

Machine Learning and Systems for Building the Next Generation of EDA Tools

Claudionor Coelho - Google Inc
Manish Pandey - Synopsys, Inc.
Claudionor Coelho - Google Inc

This workshop covers the basics of machine learning, systems and infrastructure considerations for performing machine learning at scale, specialized hardware architectures for neural networks, and approaches for using machine learning for building the next generation of EDA tools. The workshop starts with Naïve Bayes, Support Vector Machines, and Decision Trees, followed by blackbox classifier training with gradient descent. With examples, the workshop illustrates feature selection, model validation and how to avoid overfitting machine learning models. Dimensionality reduction techniques become important for data with high dimensionality for reducing computational and storage requirements. We discuss singular value decomposition (SVD), and principal component analysis (PCA) techniques for dimensionality reduction. Next, the workshop discusses k-means clustering for unsupervised learning, and efficient parallel algorithms for solving this problem for large datasets. The workshop proceeds on to deep network training and simple convolutional neural networks. It covers common neural net architectures, including ResNet, and Recurrent Neural Networks (RNNs), that are commonly used for many pattern recognition tasks. We expect participants to build several small EDA based projects using Machine Learning and Deep Learning. Examples of ML/DL small projects that may include, but are not limited to.

1. Data preparation

2. Using regression to perform parameter tuning of EDA heuristics

3. Using k-means clustering to classify heuristics

4. Using convolutional networks to perform feature detection

5. Analyzing traces using recurrent networks or embeddings Attendees are expected to have basic understanding of Python and Numpy, and have a laptop computer.