Elective for CS graduate students at the Technische Hochschule Nürnberg.
Class Schedule and Credits
Time and Location:
- Mondays at 11.30a HW.307
- Tuesdays at 11.30a SP.467
Announcements and Discussions: Join on Teams wih code: endtu0s
.
Each week, we will discuss algorithms and their theory before implementing them to get a better hands-on understanding. The materials consist of a mix of required and recommended readings, slides as well as a set of mandatory programming and analysis assignments. Pair programming encouraged, BYOD strongly recommended!
Assignments
Lectures are accompanied by mandatory assignments that will be reviewed and discussed every week.
All assignments are in form of prepared python3
jupyter notebooks.
Depending on the topic, they consist of programming, evaluation and/or discussion sections.
Please submit the notebooks (including state/rendered cells) the Teams channel under Files > Assignment Submissions
(see schedule below).
Pair-programming is encouraged, but everyone needs to submit an individual file.
Credits
Credits are earned through two components:
- All assignments must be completed on time (see schedule below; pass/fail).
- Oral exam (20’) covering theory and assignments (graded; individual exams).
Note: Materials will be (mostly) in English, the lectures/tutorials will be taught in German unless English speaker present; oral exam in language of choice.
Recommended Textbooks
- Chao, K.-M. and Zhang, L.: Sequence Comparison (Springer). available online through Ohm Library
- Sun, R., Giles, L. and van Leeuwen, J.: Sequence Learning: Paradigms, Algorithms and Applications (Springer). available online through Ohm Library
- Huang, Acero, Hon: Spoken Language Processing: A Guide to Theory, Algorithm and System Development. (ISBN-13: 978-0130226167)
- Jurafsky, D and Martin, J: Speech and Language Processing. 2017 (available online)
- Manning, C, Raghavan P and Schütze, H: Introduction to Information Retrieval, Cambridge University Press. 2008. (available online)
- Goodfellow, I and Bengio,Y and Courville, A: Deep Learning. 2016 (available online)
- Schukat-Talamazzini, E.-G. Automatische Spracherkennung. 1995 (available online)
Please note the required reading remarks in the syllabus.
Schedule
Date | Topic | Required Reading | Materials | Assignment due |
---|---|---|---|---|
Mar 17 | no class | |||
Mar 18 | comparing sequences: ED/Levenshtein, NW, DTW, modeling cost; intro A1 | Chao/Zhang Ch. 1.2 through 1.4, 2.4 and 3. | introduction, comparing sequences | |
Mar 24 | no class | |||
Mar 25 | Assignment 1 | A1 Dynamic Programming | ||
Mar 31 | Markov chains: statistical modeling of discrete sequences; discussion A1, intro A2 | Schukat-Talamazzini Ch. 7.2.{1,2}, 7.3 | markov chains | |
Apr 1 | Assignment 2 | A2 Markov chains | ||
Apr 7 | HMMs, pt. 1: basics, BW, time-alignments; intro A3.1; | Schukat-Talamazzini Ch. 5 & 8 | Hidden Markov Models | A1 |
Apr 8 | review A2; Assignment 3, pt. 1 | A3 HMM | ||
Apr 14 | HMMs, pt. 2: Viterbi, beam-decoding, higher order modeling; intro A3.2 | Decoding curtesy of Elmar Nöth | A2 | |
Apr 15 | Assignment 3, pt. 2 | A3 HMM | ||
Apr 21 | no class (Easter) | |||
Apr 22 | no class (Easter) | |||
Apr 28 | nnets 1: fundamentals, FF, AE, Word2Vec, FastText, ConvNets, embeddings, HMM-DNN; intro A4 | Karpathy 2016: Yes you should understand backprop, Mikolov et al., 2013. Efficient Estimation of Word Representations in Vector Space, Waibel et al., 1989. Phoneme Recognition Using Time-Delay Neural Networks, LeCun et al., 1998. Gradient-based learning applied to document recognition | nnets basics, nnets pt.1 | A3 |
Apr 29 | Assignment 4 | A4 nnets | ||
May 5 | nnets2: RNN, LSTM, GRU; intro A5 | Pytorch Seq2Seq Tutorial, Pascanu et al. On the difficulty of training recurrent neural networks, Chris Olah Understanding LSTM Networks | slides | |
May 6 | no class | |||
May 12 | nnets3: s2s, Attn, CTC, RNN-T; intro A6 | Graves et al., 2006. Connectionist Temporal Classification: Labelling Unsegmented Sequence Data with Recurrent Neural Networks, Loren Lugosch’s Introduction to RNN-T, Graves et al., 2012. Sequence Transduction with Recurrent Neural Networks | attention, ctc, rnn-t transfer learning | A4 |
May 13 | Assignment 5 | A5 RNN | ||
May 19 | tranformers: basics, architectures for text (BERT, SBERT, GPT) and speech (Wav2Vec2); intro A8 | Łukasz Kaiser: Attention is all you need, esp. at 15:45ff. Vaswani et al. Attention Is All You Need, Jay Alammar The Illustrated Transformer, Devlin et al. BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding, wav2vec: Unsupervised Pre-training for Speech Recognition, Radford et al. Improving Language Understanding by Generative Pre-Training | attention, ctc, rnn-t transfer learning | A5 |
May 20 | Assignment 6 | A6 attention | ||
May 26 | LLMs as foundation models: benchmarks, GPT, BPE, data (pretraining and fine-tuning), instructGPT, RLHL; intro A9; conditioning of transformers: zero-/few-shot, CoT | road to gpt | A6 | |
May 27 | Assignment 7 | A7 Transformers | ||
Jun 2 | no class (BV IN-2021-01) | |||
Jun 3 | Assignments (cont’d) | |||
Jun 9 | no class (Pentecost) | |||
Jun 10 | no class (Pentecost) | |||
Jun 16 | no class (summer school) | |||
Jun 17 | no class (summer school) | |||
Jun 23 | reinforcement learning | reinforcement learning | A7 | |
Jun 24 | Assignment 8 | A8 Summarization | ||
Jun 30 | state space models (tbd) | A8 | ||
Jul 1 | wrap-up | |||
Calendar Week 28 | Exam week |
Subscribe to https://github.com/sikoried/sequence-learning/ to follow updates.