The Deep Learning Series

In this series, we will cover Deep Learning. We will cover topics like: What is Deep Learning? The anatomy of a neural network. The applications of deep learning and it’s algorithms and much more.

In the past decade, AI is all the hype. Machine Learning, Deep Learning and AI are used left and right without any differenciator and it is something that is used in our daily lives most of the times without us even knowing about it!

When we think of AI, we think about our promised future: Self driving cars, chatbots better than humans and virtual assistants that you can have a conversation with. It is also painted as a grim future — a one where humans will lose jobs and/or we will be controlled by robots. For us, as people at the forefront of AI it is neccessary to differenciate between the noise and focus on making ethical strides in a technology that has the possibility of changing our lives.

Who is this for?

This series is for anyone interested in Deep Learning. You don’t need to be a MLE but the prequisties would require having a basic knowledge of Linear Algebra, a programming language (pref: Python) and that’s it.

Tech Stack and Type of Learning

We will use Keras, Python and Jupyter Notebooks for this series. Along the way, We will code out a few projects and all articles are supplemented with code as needed.

Table of contents

• What is Deep Learning?

  • Artificial Intelligence, Machine Learning and Deep Learning
  • A history of Machine Learning

• The Mathematical blocks of Neural Nets

  • A look at a neural network
  • Tensor operations
  • Gradient based optimizations

• Anatomy of neural networks

  • Layers
  • Models
  • Loss functions

• Fundaments of Machine Learning

  • Branches of Machine Learning
  • Supervised and Unsupervised Learning
  • Self-supervised Learning
  • Reinforcement Learning
  • Training, Validation, Data PreProcessing and Feature Engineering
  • Overfitting and Underfitting

• Deep Learning for:

  • Computer Vision — Convolutional Neural Networks (CNN’s)
  • Text and Sequences — Recurrent Neural Networks (RNN’s), Long Short Term Memory Nets (LSTM’s) and sequence processing with convnets.

• Generative Deep Learning

  • Text generation with LSTM’s
  • Image generation with autoencoders
  • An introduction to generative adversarial networks (GAN’s)

Ready to get started? Let’s jump right into it.