An overview of gradient descent optimization algorithms: ADAM, RMSPROP, MOMENTUM, etc.
From zero to research — An introduction to Meta-learning Model Agnostic, Learning to learn, LSTM, cordinatewise, L-BFGS, BPTT
How to handle large datasets in python with pandas and dask python, pandas, dask, large dataset
Where to place the Dropout layer in CNN: Hinton suggested that you should place it after each fully connected layers
Facebook Comments