To do

  • Watch lecture 4: backpropagation and neural nets (part 1)
  • Start implementing Q-Learning for the tictactoe learning algorithm
    • A different reinforcement learning approach that uses a neural net
  • Start collecting dash cam driving videos for our dataset
  • Download Geoff Hinton’s Neural Net course videos from Coursera

Done

  • Watched lecture 4 of CS231n and the chain rule video
  • Downloaded (at home):
    • Analysis of Algorithms
    • Algorithms I
    • Algorithms II
    • Probabilistic Graphical Models
    • Neural Networks and Machine Learning