https://github.com/lresende/machine-learning-presentations
🤖 ML presentations from the Stash #ml-papers reading club
https://github.com/lresende/machine-learning-presentations
Last synced: 7 months ago
JSON representation
🤖 ML presentations from the Stash #ml-papers reading club
- Host: GitHub
- URL: https://github.com/lresende/machine-learning-presentations
- Owner: lresende
- Created: 2021-08-26T07:11:40.000Z (about 4 years ago)
- Default Branch: master
- Last Pushed: 2020-07-17T14:10:27.000Z (about 5 years ago)
- Last Synced: 2025-01-17T09:36:52.028Z (9 months ago)
- Size: 35.7 MB
- Stars: 0
- Watchers: 2
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# About
Since the start of 2019 the Data Science team at Stash has been holding a monthly research paper reading club. Members submit interesting machine-learning related papers and at the end of each month we vote on a paper, splt up the sections among volounteers, present it and hold a discussion.
This repo contains an archive of slide decks we have generated, indexed below:
**2/19** - Hidden Technical Debt in Machine Learning Systems
[[slides](slides/hidden-technical-debt-in-machine-learning-systems-slides.pdf)]
[[paper](resources/hidden-technical-debt-in-machine-learning-systems.pdf)]
**3/19** - Bayesianism and causality, or, why I am only half-Bayesian
[[slides](slides/bayesianism-and-causality-or-why-i-am-only-half-bayesian-slides.pdf)]
[[paper](resources/bayesianism-and-causality-or-why-i-am-only-half-bayesian.pdf)]
**5/19** - Inferring Causal Impact Using Bayesian Structural Time-Series Models
[[slides](slides/inferring-causal-impact-using-bayesian-structural-time-series-models-slides.pdf)]
[[paper](resources/inferring-causal-impact-using-bayesian-structural-time-series-models.pdf)]
**6/19** - Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks
[[slides](slides/modeling-long-and-short-term-temporal-patterns-with-deep-neural-networks-slides.pdf)]
[[paper](resources/modeling-long-and-short-term-temporal-patterns-with-deep-neural-networks.pdf)]
**7/19** - Applying Deep Learning To Airbnb Search
[[slides](slides/applying-deep-learning-to-airbnb-search-slides.pdf)]
[[paper](resources/applying-deep-learning-to-airbnb-search.pdf)]
**8/19** - Deep Learning and Long Term Investing
[[slides](slides/deep-learning-and-long-term-investing-slides.pdf)]
[[paper](https://www.euclidean.com/data-posts-machine-learning)]
**9/19** - The empirical risk-return relation: a factor analysis approach
[[slides](slides/the-empirical-risk-return-relation-a-factor-analysis-approach-slides.pdf)]
[[paper](resources/the-empirical-risk-return-relation-a-factor-analysis-approach-slides.pdf)]
**10/19** - Hierarchical Topic Models and the Nested Chinese Restaurant Process
[[slides](slides/a-hidden-markov-model-of-customer-relationship-dynamics-slides.pdf)]
[[paper](resources/a-hidden-markov-model-of-customer-relationship-dynamics.pdf)]
**11/19** - A Hidden Markov Model of Customer Relationship Dynamics
[[slides](slides/a-hidden-markov-model-of-customer-relationship-dynamics-slides.pdf)]
[[paper](resources/a-hidden-markov-model-of-customer-relationship-dynamics.pdf)]
**12/19** - Semi-supervised Sequence Learning
[[slides](slides/semi-supervised-sequence-learning-slides.pdf)]
[[paper](resources/semi-supervised-sequence-learning.pdf)]
**1/20** - code2vec: Learning Distributed Representations of Code
[[slides](slides/code2vec-learning-distributed-representations-of-code-slides.pdf)]
[[paper](resources/code2vec-learning-distributed-representations-of-code.pdf)]
**2/20** - Learning to Predict by the Methods of Temporal Differences
[[slides](slides/learning-to-predict-by-methods-of-temporal-differences-slides.pdf)]
[[code](resources/learning-to-predict-by-methods-of-temporal-differences-code.ipynb)]
[[paper](resources/learning-to-predict-by-methods-of-temporal-differences.pdf)]
**3/20** - Automatic Detection and Diagnosis of Biased Online Experiments
[[slides](slides/automatic-detection-and-diagnosis-of-biased-online-experiments.pdf)]
[[paper](resources/automatic-detection-and-diagnosis-of-biased-online-experiments.pdf)]
**5/20** - NSTM: Real-Time Query-Driven News Overview Composition at Bloomberg
[[slides](slides/NSTM-real-time-query-driven-news-overview-composition-at-bloomberg.pdf)]
[[paper](resources/NSTM-real-time-query-driven-news-overview-composition-at-bloomberg.pdf)]