Stanford Seminar - ML Explainability Part 2 I Inherently Interpretable Models

Показать описание

Professor Hima Lakkaraju presents some of the latest advancements in machine learning models that are inherently interpretable such as rule-based models, risk scores, generalized additive models and prototype based models.

#machinelearning

0:00 Introduction
0:06 Inherently Interpretable Models
4:41 Bayesian Rule Lists: Generative Model
8:39 Pre-mined Antecedents
11:09 Interpretable Decision Sets: Desiderata
12:16 IDS: Objective Function
15:47 IDS: Optimization Procedure
16:46 Risk Scores: Examples
18:59 Objective function to learn risk scores
21:54 Generalized Additive Models (GAMs)
23:00 Formulation and Characteristics of GAMS
30:04 Prototype Selection for Interpretable Classification
34:00 Prototype Layers in Deep Learning Models
40:01 Attention Layers in Deep Learning Models

Рекомендации по теме

Комментарии

Models with straightforward explanations.
2:10 Rules-based.
16:40 Risk scores.
21:55 Generalized additive.
30:35 Prototype-based.
42:40 Attention-based.

anonviewerciv

can we get the implementation of the discussed interpretability techniques?

LakshmiKeerthana-jqqj

What is the name of the paper discussed in tht workshop??

hammadwahab

Stanford Seminar - ML Explainability Part 2 I Inherently Interpretable Models

Stanford Seminar - ML Explainability Part 1 I Overview and Motivation for Explainability

Stanford Seminar - ML Explainability Part 5 I Future of Model Understanding

Stanford Seminar - ML Explainability Part 3 I Post hoc Explanation Methods

Stanford Seminar - ML Explainability Part 4 I Evaluating Model Interpretations/Explanations

Stanford Seminar - ML Explainability Part 2 I Inherently Interpretable Models

Stanford Seminar - How can you trust machine learning? Carlos Guestrin

Distributed ML with H2O feat. Erin LeDell | Stanford MLSys Seminar Episode 23

MedAI Session 22: Explainable AI - from generalities to time series | Jonathan Crabbé

Interpretable vs Explainable Machine Learning

AWS re:Invent 2020: Interpretability and explainability in machine learning

Explainable AI explained! | #1 Introduction

Stanford Seminar - Democratizing Robot Learning

Bridging Models and Data feat. Willem Pienaar | Stanford MLSys Seminar Episode 32

What can Data-Centric AI Learn from Data and ML Engineering? - Alkis Polyzotis | Stanford MLSys #65

The Missing Link in ML Infrastructure feat. Josh Tobin | Stanford MLSys Seminar Episode 11

Causal AI for Systems feat. Pooyan Jamshidi | Stanford MLSys Seminar Episode 38

MFML 017 - Explainability and AI

Model explainability - Idan Angel - PyCon Israel 2019

Stanford MLSys Seminar Episode 2: Matei Zaharia

Machine Learning Community Standup - Model Explainability

Carlos Guestrin: How Can You Trust Machine Learning?

Stanford Seminar - Human-AI Interaction Under Societal Disagreement

Interpreting ML models with explainable AI

MedAI #34: Optimizing for Interpretability in Deep Neural Networks | Mike Wu