This Mini Series covers the basic of Deep Learning guiding the user in a learn by experiments journey. This series is split in 4 Episode of increasing difficulties:
The beginner episode is split in 4 part:
- FloydHub introducting to Deep Learning covers an high level overview what is DL, why it is become mainstream, what are the current challenges and in which direction researchers are looking for.
- FH intro to DL: PyTorch covers the PyTorch Deep Learning Framework.
- FH intro to DL: Linear Regression covers the ML workflow and the classical house prediction regression problem solved with a Linear Regression model.
- FH intro to DL: Logistic Regression covers the MNIST dataset and the Logistic Regression model to classify it. This end the overview of the basic building blocks which allow us to go deeper.
The intermediate episode is split in 3 part:
- FH intro to DL: NN covers NN
- FH intro to DL: ConvNet covers CNN
- FH intro to DL: Transfer Learning covers Transfer Learning