Recurrent Neural Networks and Models of Computation - Edward Grefenstette, DeepMind
Alan Turing Institute via YouTube
Overview
Save Big on Coursera Plus. 7,000+ courses at $160 off. Limited Time Only!
Explore the intersection of recurrent neural networks and traditional models of computation in this insightful talk by Edward Grefenstette from DeepMind. Delve into the analysis of various recurrent architectures, comparing simpler models to finite state automata and examining how memory-enhanced structures improve algorithmic efficiency. Investigate sequence translation, learning to execute, language modeling, and experiments in computational hierarchy. Discover the role of attention mechanisms, readonly memory, and architectural bias in neural networks. Gain a deeper understanding of the relationship between logic and learning in complex systems, and how combining these approaches can lead to powerful solutions in artificial intelligence and formal reasoning.
Syllabus
Introduction
Sequence Translation
Learning to Execute
Language Modeling
Experiments
Computational Hierarchy
Data Efficiency
Recurrent Networks
Attention
Attention to Sequence
Limitations
Readonly memory
Turing machine
Pushdown automata
Architectural Bias
Conclusion
Taught by
Alan Turing Institute