Dexa
/
Machine Learning Street Talk (MLST)
Learn more
Follow
Model Information Encoding
Tim and Alex discuss the importance of inductive priors in models to facilitate learning. The conversation delves into the necessity of biases in deep learning models like CNNs for improved generalization and efficiency.
Add to Radar
Share
In this clip
Tim Scarfe
Alex Stenlake
From this podcast
Machine Learning Street Talk (MLST)
#035 Christmas Community Edition!
Related Questions
Are there biases in AI as discussed in the episode More Language, Less Labeling with Kate Saenko - #580 and the clip Image Captioning Advances?