There are no official pre-requisites for this course but it would help if you have done the following courses (preferably in the order mentioned below) :

Calculus [Online course from MIT]

Linear Algebra [CS6015 or equivalent] | [Online course from MIT]

Probability Theory [CS6015 or equivalent] | [Online course from MIT]

Non-linear Optimization [CS5020 or equivalent] | [First Course in Optimization by Prof. Soman (IITB) available on CDEEP]

Pattern Recognition and Machine Learning [CS5691 or equivalent] | [Andrew Ng's ML course]

Deep Learning [CS7015 or equivalent]

**Instructor**: Mitesh M. Khapra**When**: Jan-May 2019**Lectures**: Slot K**Where**: CS24, CS Building, First Floor-
**Teaching Assistant**Name Lab Email Working hours Days Preksha Nema RISE Lab preksha.nema9@gmail.com 2-4 pm Wed,Fri

40% Project |30% Assignment | 10% Paper Summary | 20% Mini Quiz

Lecture | Contents | Papers/Slides | Blogs |
---|---|---|---|

Lecture 0 | Course Overview | S | - |

Lecture 1 | Overview of Word Embeddings | S | - |

Lecture 2 | ELMo | P | - |

Lecture 3 | Attention Is All You Need | P | B |

Lecture 4 | BERT | P | - |

Lecture 5 | What Bert Learns ? | P | - |

Lecture 6 | XL Net | P | B |

Lecture 7 | Eernie | P | B |

Lecture 8 | QA - Datasets | Survey | - |

Lecture 9 | QA - Overview | S1 | - |

Lecture 10 | QA - CharEmbedding/CoAttention | S1 | S2 | BiDAF | DCN | QANet Paper | QANet Slides |

Lecture 11 | QA - SingleFramework | S1 | - |

Lecture 12 | Overview of Object Detection | - | B |

Lecture 13 | RCNN, Fast RCNN, Faster RCNN | S | P1 | P2 | P3 | B1 | B2 | B3 |

Lecture 14 | YOLO | S | P1 | P2 | P3 | B |

Lecture 15 | Retina Net | P | B |

Lecture 16 | Single Shot Learning | S | B |

Lecture 17 | Video Datasets Overview | P | B |

Lecture 18 | Optical Flow | P1 | P2 | B1 | B2 |

Lecture 19 | Action Recognition | P | B |

Lecture 20 | Action Recognition (Contd.) | P1 | P2 | B |

Lecture 21 | Graph Representation Learning | S1 | S2 | - |

Lecture 22 | Graph Representation Learning (Contd.) | S | - |

Lecture 23 | Graph Convolutional Networks | P | - |