Previous: W5, Next: W7
Lecture 24: Slides.
(Sorry about the inconsistent file names: these topics were not covered in 2019)
Lecture 23 Part 2: Link
Lecture 23 Part 3: Link
Lecture 24 Part 1: Link
Lecture 24 Part 2: Link
Lecture 24 Part 3: Link
Lecture 23 Part 3 and Lecture 24 Part 2 and 3 about training algorithms for Hidden Markov Models and Recurrent Neural Networks are completely optional. Treat the other parts as reviews for the previous lecture, no questions directly related to HMM and RNN will be on the exams.
Lectures 11 and 12 videos will not be uploaded until after the midterm.
LTSM and GRU: Link
# Summary
📗 Examples and quizzes: E6
📗 Monday lecture: 5:30 to 8:30, Guest Link
📗 Wednesday math homework office hours: 5:00 to 6:00, Guest Link
📗 Thursday math homework office hours: 5:00 to 6:00, Guest Link
📗 Friday office hours for other things: 5:00 to 6:00, Guest Link
# Lectures
📗 Slides
Lecture 23: Slides. Lecture 24: Slides.
(Sorry about the inconsistent file names: these topics were not covered in 2019)
📗 Videos
Lecture 23 Part 1: Link Lecture 23 Part 2: Link
Lecture 23 Part 3: Link
Lecture 24 Part 1: Link
Lecture 24 Part 2: Link
Lecture 24 Part 3: Link
📗 Notes
Typo: Lecture 23 Viterbi Algorithm the recursive formula should be V_t,k = max ... V_t-1,k, not V_1,k. Lecture 23 Part 3 and Lecture 24 Part 2 and 3 about training algorithms for Hidden Markov Models and Recurrent Neural Networks are completely optional. Treat the other parts as reviews for the previous lecture, no questions directly related to HMM and RNN will be on the exams.
Lectures 11 and 12 videos will not be uploaded until after the midterm.
# Other Materials
📗 Relevant websites
RNN Visualization: Link LTSM and GRU: Link
📗 YouTube videos from 2019
These topics were not covered in 2019 Last Updated: November 09, 2021 at 12:30 AM