Interpretable Machine Learning with Serg Masis

The Minhaaj's Podcast

Serg Masis is the author of best-selling book 'Interpretable Machine Learning with Python' and senior Data Scientist at Sygenta. He has mentored many data scientists around the world.

Timestamps:

00:00 intro

08:30 Old 4.77 MH z Computer, Late 80s and Programming

11:51 Fairness, Accountability and Transparency in Machine Learning, Startup and Harvard

16:33 Fairness vs Preciseness, Bias and Variance Tradeoff, Are Engineers to blame?

21:43 Mask-Detection Problem in Coded-Bias, Biased Samples, Surveillance using CV

32:38 Fixing Biased Datasets, Augmenting Data and Limitations

37:39 Algorithmic Optimisation and Explainability

40:51 Eric Schmidt on Behavioral Prediction, SHAP values, Tree and DeepExplainers

44:50 Challenges of using SHAP and LIME & Big Data

49:37 GPT3, Large Models and ROI on Explainability

01:00:00 TCAS, Collision Risks and Interpretability, Ransom Attacks

01:08:09 Guitar, Bass, and Led Zepplin

01:09:31 Birth Order and IQ, Science vs Folk Wisdom

01:13:30 Reverse Discrimination & Men, Bias in Child Custody, Prison Sentences, and Incarceration

01:23:11 Receidivism to Criminal Behaviour, Ethnic over-representation & Systematic Racism

01:24:44 Human Judges vs AI, Absolute Fairness, Food and Parole

01:30:20 Face Detection in China, Privacy vs Convenience, Feature Engineering and Model Parsimony

01:35:51 Sparsity, Interaction Effects, and Multicollinearity

01:38:23 Four levels of Global and Local Predictive Explainability

01:43:17 Recursive and Sequential Feature Selection

01:47:42 Ensemble, Blended and Stacked Models and Interpretability

01:53:45 In-Processing and Post-Processing Bias Mitigation

01:57:00 Future of Interpretable AI

--- Send in a voice message: https://podcasters.spotify.com/pod/show/minhaaj/message