Introduction to Deep Learning

Course can be found here

Notebook for quick search can be found here

• Week 1 Introduction to optimization

  • Train a linear model for classification or regression task using stochastic gradient descent
  • Tune SGD optimization using different techniques
  • Apply regularization to train better models
  • Use linear models for classification and regression tasks
  • Linear models and optimization

• Week 2 Introduction to neural networks

  • Explain the mechanics of basic building blocks for neural networks
  • Apply backpropagation algorithm to train deep neural networks using automatic differentiation
  • Implement, train and test neural networks using TensorFlow and Keras
  • Going deeper with Tensorflow
  • my1stNN
  • Getting deeper with Keras
  • Your very own neural network

• Week 3 Deep Learning for images

  • Define and train a CNN from scratch
  • Understand building blocks and training tricks of modern CNNs
  • Use pre-trained CNN to solve a new task
  • Your first CNN on CIFAR-10
  • Week 3 PA 2 Fine-tuning InceptionV3 for flowers classification

• Week 4 Unsupervised representation learning

  • Understand what is unsupervised learning and how you can benifit from it
  • Implement and train deep autoencoders
  • Apply autoencoders for image retrieval and image morphing
  • Implement and train generative adversarial networks
  • Understand basics of unsupervised learning of word embeddings
  • Autoencoders

• Week 5 Deep learning for sequences

  • Define and train an RNN from scratch
  • Understand modern architectures of RNNs: LSTM, GRU
  • Use RNNs for different types of tasks: sequential input, sequential output, sequential input and output
  • Generating names with RNNs

• Week 6 Final Project

  • Image Captioning Final Project