Explore >> Select a destination
|
You are here 
|
anima-ai.org | ||
| | | | |
blog.research.google
|
|
| | | | | ||
| | | | |
evjang.com
|
|
| | | | | In my essay "Just ask for Generalization", I argued that some optimization capabilities, such as reinforcement learning from sub-optimal trajectories, might be better implemented by generalization than by construction. We have to generalize to unseen situations at deployment time anyway, so why not focus on generalization capability as the first class citizen, and then "just ask for optimality" as an unseen case? A corollary to this design philosophy is that we should discard inductive biases that introd... | |
| | | | |
dennybritz.com
|
|
| | | | | Deep Learning is such a fast-moving field and the huge number of research papers and ideas can be overwhelming. | |
| | | | |
dennybritz.com
|
|
| | | This the thirdpart of the Recurrent Neural Network Tutorial. | ||
