Palash Shah

will be creating an interactive dashboard giving the user statistics about their dataset if `.dashboard()` is called.

self explanatory.

use taBert for instruction identification (enhance instruction identification)

1

new pretrained algorithm for action identification; can probably be used for the identification of instructions.

create tuning for NLP

1

we need to be able to call `.tune()` for NLP tasks. Look into keras-tuner for this.

look into optuna

currently we're using random-search from keras-tuner. Instead we should be using probabilistic models

look into implementing some sort of reinforcement learning query? how are most users setting up these queries. This is a bit more difficult because RL problems require action and agents...

how can we support different architectures for keras models that users have already created?

https://causalnex.readthedocs.io/en/latest/03_tutorial/03_tutorial.html