YoVDO

Programming with Neural Surrogates of Programs

Offered By: Neurosymbolic Programming for Science via YouTube

Tags

Neural Networks Courses Deep Learning Courses Transformer Architecture Courses Neurosymbolic Programming Courses

Course Description

Overview

Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the concept of neural surrogates in programming through this insightful talk by Alex Renda from MIT CSAIL. Delve into three case studies of surrogate-based design patterns, evaluated using a large-scale CPU simulator. Learn about two innovative approaches for constructing optimal program surrogates: the Renamer, a Transformer architecture invariant to semantics-preserving variable renaming, and Turaco, a methodology for sampling datasets to train neural network-based surrogates. Gain valuable insights into programming methodologies in the era of deep learning and discover how surrogates can enhance the speed and accuracy of complex programs.

Syllabus

Programming with Neural Surrogates of Programs


Taught by

Neurosymbolic Programming for Science

Related Courses

AI for Scientists: Accelerating Discovery through Knowledge, Data and Learning
Neurosymbolic Programming for Science via YouTube Probabilistic Programming Tutorial - Part 1
Neurosymbolic Programming for Science via YouTube Model-Based Reasoning in Neurosymbolic Programming for Science
Neurosymbolic Programming for Science via YouTube Moving Beyond the First Portrait of Our Milky Way's Black Hole by Leveraging Underlying Structure
Neurosymbolic Programming for Science via YouTube Neurosymbolic Program Architecture Search Methods - Session 3
Neurosymbolic Programming for Science via YouTube