Deep Learning Study

---

This study will consist

• Learning theoretical basis of deep learning
• Writing deep learning applications
• Implementing main project
• Reading ML Papers

Week1 (Jul 14)

• Basics of GIT
• Basics of ML
• Setting up environment
• Project discussion

Week2 (Jul 21)

• ANN, DNN

  • Implementing simple ANN classifying handwritten numbers
  • Implementing DNN (Deep neral network) classifying images

• Theroretical basics

  • Activation function, Loss function
  • Back propagation, Optimizers

• Paper reading

  • Understanding the difficulty of training deep feedforward neural networks (Xavier Glorot, Yoshua Bengio - Université de Montréal)

Week3 (Jul 27)

• CNN, RNN, LSTM

  • Implementing image classifier using CNN
  • Implementing Movie preference predictor using RNN, LSTM

• Theoretical basics

  • CNN (Convolutional neural network)
  • RNN, LSTM(Recurrent neural networks)

• Paper reading

  • Understanding and Predicting Image Memorability at a Large Scale (Aditya Khosla, Akhil S. Raju, Antonio Torralba, Aude Oliva - MIT)

Week4 (Aug 4)

• NLP(Natural language processing)

  • Word2Vec (Skip-gram, CBOW)
  • Seq2Seq (If possible)

• Therertical basics

  • Word2Vec (Word to vector)

• Paper reading

  • Conversations Gone Awry: Detecting Early Signs of Conversational Failure (Justine Zhang and Jonathan P. Chang and Cristian Danescu-Niculescu-Mizil - Cornell University)

Week5 (Aug11)

• Main project + Further study

Week6 (Aug18)

• Main project + Further study