Deep Learning for Symbolic Mathematics | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
22,300
Published on ● Video Link: https://www.youtube.com/watch?v=8WmWwpflB7g


Duration: 56:39
1,318 views
45

For slides and more information on the paper, visit https://aisc.ai.science/events/2020-02-18

Discussion lead/authors: Francois Charton, Guillaume Lample

Abstract:
Neural networks have a reputation for being better at solving statistical or approximate problems than at performing calculations or working with symbolic data. In this paper, we show that they can be surprisingly good at more elaborated tasks in mathematics, such as symbolic integration and solving differential equations. We propose a syntax for representing mathematical problems, and methods for generating large datasets that can be used to train sequence-to-sequence models. We achieve results that outperform commercial Computer Algebra Systems such as Matlab or Mathematica.

Authors: Guillaume Lample, François Charton



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-03-04Can deep learning AI help with detecting COVID-19/coronavirus?
2020-03-03Daniel Lemire: The research paper should NOT be the final product | AISC
2020-02-29Model Packaging Overview (NLP + MLOps workshop sneak peak)
2020-02-26[hgraph2graph] Hierarchical Generation of Molecular Graphs using Structural Motifs | AISC Spotlight
2020-02-25AISC | Women in AI | Dec 2019
2020-02-25Build and Deploy NLP models | NLP Overview
2020-02-25Protein secondary structure detection in intermediate-resolution cryo-EM maps using deep learning |
2020-02-24[AI Product] How to build products people actually want to use | AISC
2020-02-20Build and Deploy Machine Learning Models | MLOps Overview
2020-02-19Quantifying the dynamics of failure across science, startups and security | AISC
2020-02-18Deep Learning for Symbolic Mathematics | AISC
2020-02-12Visualizing and measuring the geometry of BERT | AISC
2020-02-11Attention is not not explanation + Character Eyes: Seeing Language through Character-Level Taggers |
2020-02-10Single Headed Attention RNN: Stop Thinking With Your Head | AISC
2020-01-27Identifying Big ML product opportunities inside Big organizations | AISC
2020-01-23Machine Learning in Cyber Security, Overview | AISC
2020-01-22BottleSum: Unsupervised & Self-supervised Sentence Summarization w/ Information Bottleneck Principle
2020-01-20A Hybrid GA-PSO Method for Evolving Architecture and Short Connections of Deep Convolutional Neural
2020-01-13Plug and Play Language Models: A Simple Approach to Controlled Text Generation | AISC
2020-01-08Overview of Modern Anomaly and Novelty Detection | AISC
2020-01-06Annotating Object Instances With a Polygon RNN | AISC


Tags:
deep learning
symbolism
machine learning
representation learning
ai
artificial intelligence
agi
artificial general intelligence