Moshe Sipper
  • Home
  • Publications
  • Books
  • Research
  • Teaching
  • Blog
  • Comic Sip
  • Songs

Advanced Seminar in Intelligent Systems
סמינר מתקדם במערכות נבונות​

Machine Learning
202-2-1551 ​Spring 2021 סמסטר ב
Lecturer: Prof. Moshe Sipper
Course Description
  • Each student will give a talk on a topic or a paper from the research literature.
  • Attendance is mandatory.
  • A partial list of papers/topics is given below — you're encouraged to suggest your own.
  • ​Presentation length: 45 minutes. 2 talks each week.
  • Please email me your presentation a few days before your talk.
  • Each student must submit a 1-paragraph summary, along with scores, for each of the 2 weekly talks. [scoring rubric: organization/25, knowledge/25, text/20, graphics/20, elocution/7, eye contact/3]
Topics
  • Machine learning in practice: evaluation, dataset splits, cross-validation, performance measures, bias/variance tradeoff
  • Supervised learning: models, features, objectives, model training, overfitting, regularization
  • Linear and logistic regression
  • Bagging
  • Boosting
  • Clustering, k-means
  • Artificial neural networks
  • Deep learning​
  • ML as part of (the) data science (pipeline)
Some papers
  • A Few Useful Things to Know About Machine Learning
  • Classification: Basic Concepts, Decision Trees, and Model Evaluation
  • Decision trees: an overview and their use in medicine
  • Data clustering: 50 years beyond K-means
  • Boosting algorithms: A review of methods, theory, and applications
  • Random Forests​
Literature, vids, datasets, and other resources
Lectures
Eyal S, Evolution Strategies as a Scalable Alternative to Reinforcement Learning
​Raz L, Classification: Basic Concepts, Decision Trees, and Model Evaluation
Zvika H, Generative adversarial networks
Nitzan C, Sequence to Sequence Learning with Neural Networks
Snir T, Bagging, random forests
Ron K, POMDP/MDP/RL
Arnon I, Which Tasks Should Be Learned Together in Multi-task Learning
Amir B, Can You Trust Your Model’s Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shift
Yael A, Auto-encoders
Tomer L, Federated Learning
Eden A, Dynamic Routing Between Capsules
​Oz M, Unitary Evolution Recurrent Neural Networks
Or N, Data clustering: 50 years beyond K-means
​Omer K, clustering
​Linor H, Towards Effective Deep Learning for Constraint Satisfaction Problems
Shay K, Siamese Neural Networks for One-shot Image Recognition

Ella A, multimodal machine learning
Amir S, Attention is all you need
Schedule (may change)
Mar 1/ Moshe Sipper
Mar 8/ Eyal S + ​Raz L
Mar 15/ Zvika H + Nitzan C
Mar 22/ Tomer L + Tal S
Mar 29/ pesach
Apr 5/ Snir T + Arnon I
Apr 12/ Amir B + Yael A
Apr 19/ Eden A
Apr 26/ Ron K
May 3/ Orad R
May 10/ Amir S 
May 17/ shavuot
May 24/ Oz M + Or N
May 31/ Shay K + Ella A
Jun 7/ Omer K
​Jun 14/ Linor H
  • Home
  • Publications
  • Books
  • Research
  • Teaching
  • Blog
  • Comic Sip
  • Songs