Главная
Study mode:
on
1
Intro
2
Al for Bio-Medical Sciences (AIMS) Lab
3
Overview
4
Published Al models detect COVID-19 in chest X-rays
5
What was the training data for these published models?
6
How can we test how robust the models are?
7
How robust are the models?
8
What is important for the model's predictions?
9
Can we fix shortcut learning with improved data?
10
Conclusions
11
Acknowledgements
12
Outline
13
Explainable AI
14
Examples
15
Intuition
16
The recipe
17
Unified framework
18
SHAP's ingredients
19
Human-friendly
20
Game-theoretic
21
Information-theoretic
22
Choosing optimal combinations is hard
23
This is the perfect opportunity for predictive models
24
In high stakes scenarios, models should be interpretable
25
A simple fix: ensemble attributions
26
Interpretability uncovers transcriptional programs
27
Bringing Interpretable Models to Cancer Precision Medicine
28
Contrastive Analysis
29
Latent Variable Models
30
VAE Model
31
Problem
32
Contrastive Latent Variable Model
33
Background datasets
34
Contrastive VAE
35
Inspecting the salient latent values
Description:
Explore cutting-edge research in AI and machine learning applications for life sciences in this 53-minute Allen School Colloquium featuring the AIMS Research Group. Dive into recent advancements in explainable AI, computational biology, and medicine, including COVID-19 detection in medical imaging, synergistic drug combinations for cancer treatment, and contrastive latent variable modeling for biological discovery. Learn about the challenges and opportunities in integrating AI/ML with life sciences, from developing interpretable models to identifying causes and treatments for diseases like cancer and Alzheimer's. Gain insights from PhD students and researchers as they discuss their work on efficient algorithms, theoretical foundations, and practical applications of AI in high-stakes domains such as healthcare and precision medicine.

Integrating AI and Machine Learning in Life Sciences - Allen School Colloquia

Paul G. Allen School
Add to list
0:00 / 0:00