Virtual Meetup – Terence Parr

Abstract

One of the biggest challenges when writing code to implement deep learning networks is getting all of the matrix and vector (tensor) dimensions to line up properly. It’s really easy to lose track of tensor dimensionality in complicated expressions involving multiple tensors and tensor operations.  Python exceptions generated by the various libraries (Tensorflow, PyTorch, JAX, and Numpy) are often less than helpful. Worse, exceptions are generated only on a Python-line level, not subexpression. Instead of forcing programmers to manually injecting print statements prior to offending lines of code, [TensorSensor](https://github.com/parrt/tensor-sensor) uses language engineering to automatically clarify matrix-related exceptions by visualizing matrix dimensionality, and at the subexpression level.

Expository image link: https://explained.ai/tensor-sensor/images/teaser.png
Accompanying article: https://explained.ai/tensor-sensor/index.html

Biography

Terence is a professor of computer science and data science at the University of San Francisco where he continues to work on his ANTLR parser generator. Until January 2014, Terence was the graduate program director for the computer science and was founding director of analytics (now data science). Before entering academia in 2003, he worked in industry and co-founded jGuru.com. Terence herded programmers and implemented the large jGuru developers website, during which time he developed and refined the StringTemplate engine. Terence has consulted for and held various technical positions at companies such as Google, Salesforce, Sun Microsystems, IBM, Lockheed Missiles and Space, NeXT, and Renault Automation. Terence holds a Ph.D. in Computer Engineering from Purdue University.

Terence Parr: https://parrt.cs.usfca.edu/, https://www.linkedin.com/in/terence-parr-33530/

You can find the slides of the talk here.

How to join the event:

To avoid security issues is now necessary to register for the meeting. The registration should be necessary just once and be valid for all the next meetings you will participate in. Follow these steps:

1. Register yourself to the community on the Homepage
2. You will receive a confirmation email containing all the information about joining the meeting.
3. Add to your calendar
4. Enjoy the talk and, if you feel like, discuss further on the community forum