Unsupervised Learning

REGRESSION

Why we need activation function

Hyperparameter Tuning

Why do we need non-linear activation functions

Weight Initialisation

Gradient Checking

Different Batch Gradients - BGD, SBGD

Vanishing Gradients

RNN

LSTM VS GRU VS RNN

Word2Vec vs Glove

Word Embeddings - SkipGram vs CBOW

Negative Sampling

Embeddings -

Given three sentences:

• Tom went to the bank to make a payment on his mortgage.
• Yesterday my wife went to the credit union and withdrew $500.
• My friend was fishing along the river bank, slipped and fell in the water.