Modeling Human Cognition with RNNs and Curriculum Learning, w/ Kanaka Rajan - #524
Analysis
This article from Practical AI discusses Kanaka Rajan's work in bridging biology and AI. It highlights her use of Recurrent Neural Networks (RNNs) to model brain functions, treating them as "lego models" to understand biological processes. The conversation explores memory, dynamic system states, and the application of curriculum learning. The article focuses on reverse engineering these models to understand if they operate on the same principles as the biological brain. It also touches on training, data collection, and future research directions.
Key Takeaways
- •Kanaka Rajan uses RNNs to model brain functions.
- •She employs "lego models" to mimic and understand biological brain processes.
- •Curriculum learning is a key training method used in her research.
“We explore how she builds “lego models” of the brain that mimic biological brain functions, then reverse engineers those models to answer the question “do these follow the same operating principles that the biological brain uses?””