Learning Torch
Learning to program in Lua using "Torch" and other useful libraries
Torch is a scientific computing framework for LuaJIT.
Why learn Torch?
- comes with a large ecosystem of community-driven packages in ML, CV, etc
- is easy to use and efficient
- can build arbitrary graphs of neural networks, and parallelize them over CPUs and GPUs in an efficient manner
TODO
- Go through Torch documentation and try using useful functions.
- Go through other useful modules and try to use them.
- Start implementing something real
- Read and process process data as needed by the network.
- Read
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translationand implement a GRU. - Read
LSTM: A Search Space Odysseyand implement LSTM. - Use Tree LSTM in place of LSTM.
PaperCodeSlides
- Go through
Penlightdocumentation - Go through
Moses - Go through
nnmodule documentation and check how some to the functionality is implemented
Resources:
- Curated list of Torch tutorials:
link - Awesome Recurrent Neural Networks:
link - Neural Network Papers:
link - Awesome Deep Learning:
link