Categories

All (25)

AI & society (2)

Active learning (2)

Agriculture (1)

Alphafold (1)

Athletics (1)

Audio search (1)

Autoencoder (1)

Benchmarking (2)

Bias (2)

Biology (5)

Biophysics (1)

Boosting (1)

Business (1)

CIFAR (1)

CLIP (1)

CNN (2)

CNN-LSTM (1)

CSI (1)

Clustering (2)

ComBEE (1)

Computer vision (6)

Conformer (1)

Contrastive learning (3)

Cross Labs AI (1)

DeTox (1)

Decision trees (1)

Deep learning (13)

Diffusion (1)

Drug synergy (1)

EHR (1)

Early-fusion (1)

Ecology (1)

Ethical AI (3)

Exploring AI@UW (4)

Fairness (1)

Foundation models (3)

GenAI (2)

Genomics (3)

Healthcare (9)

Hugging Face (2)

Humanities (1)

ICCV (1)

IT Prof (1)

Image classification (1)

Image data (1)

LLM (14)

LLaVA (3)

LMM (2)

LSTM (1)

Label-efficient learning (1)

ML+X (11)

ML4MI (4)

MLOPT (1)

Medical imaging (3)

Meteorology (1)

Model sharing (1)

Multimodal learning (9)

Music (1)

NLP (3)

OOD detection (2)

Perception (1)

Physics (1)

Protein engineering (2)

Protein language models (2)

Representation learning (1)

Retrieval (1)

SILO (1)

Science communication (1)

Semi-supervised (1)

Signal processing (2)

Simulations (2)

Spectral analysis (2)

Text analysis (2)

Text mining (1)

Time-series (1)

Topic modeling (1)

Transfer learning (1)

Transformer (1)

Trustworthy AI (3)

UNET (1)

UW-Madison (23)

Ultrasound (1)

VLM (3)

ViT (2)

Videos (25)

Zero-shot learning (1)

Videos

Discover a curated collection of talks which dive into AI/ML applications and lessons learned by practitioners.

Note: A netID is required to view the ML4MI and the Exploring AI @ UW video series.

Automating Scientific Discovery: From Natural World Data to Systematic Literature Reviews

Videos

ML+X

Multimodal learning

Benchmarking

Retrieval

Computer vision

Zero-shot learning

Contrastive learning

Deep learning

CLIP

Biology

Ecology

Image data

LLM

Hugging Face

Edward Vendrow, a PhD student at MIT, presents his research on automating scientific discovery using multimodal AI. In this talk, he explores how AI can accelerate research…

Learning Through Comparison: Use Cases of Contrastive Learning

Videos

ML+X

UW-Madison

Deep learning

Contrastive learning

Clustering

OOD detection

Multimodal learning

Trustworthy AI

Representation learning

CIFAR

Contrastive learning is reshaping how models learn, driving widespread progress in feature learning, clustering, out-of-distribution detection, and multimodal applications.…

Yin Li, Chris Endemann

AlphaFold and Protein Language Models

Videos

ComBEE

UW-Madison

Biology

Protein engineering

LLM

Deep learning

Alphafold

Transformer

Protein language models

In a talk hosted by the University of Wisconsin-Madison’s Computational Biology, Ecology, and Evolution (ComBEE) community, Dr. Hannah Wayment-Steele discusses AlphaFold, an…

Hannah Wayment-Steele

AI for Music and the Humanities

Videos

ML+X

UW-Madison

Deep learning

GenAI

AI & society

Conformer

Humanities

Audio search

Music

CSI

Signal processing

Spectral analysis

LLM

1. What Tune Is That: A Humanities Application of Deep Learning — Alan Ng
2. Fake Artists, Fake Listeners: AI and the Music Industries — Jeremy Morris, PhD

Alan Ng, Jeremy Morris

Using Electronic Health Record Data to Predict Deterioriation in Hospitalized Children

Videos

ML4MI

UW-Madison

Healthcare

NLP

Text analysis

EHR

Boosting

Decision trees

In this talk from the Machine Learning for Medical Imaging (ML4MI) community, Anoop Mayampurath (PhD) discusses the use of electronic health record (EHR) data and machine…

Anoop Mayampurath

Vision, Language, and Vision-Language Modeling in Radiology

Videos

ML4MI

UW-Madison

Medical imaging

Healthcare

VLM

ViT

UNET

LLaVA

Computer vision

CNN

LLM

Deep learning

Multimodal learning

In this talk from the Machine Learning for Medical Imaging (ML4MI) community, Tyler Bradshaw (PhD) discusses the historical context (e.g., CNN, VGG) leading up to the new…

Intro to Out-of-Distribution Detection

Videos

ICCV

OOD detection

Trustworthy AI

The below tutorial from Sharon Li, an Assistant Professor in the Department of Computer Sciences at the University of Wisconsin-Madison, introduces a pervasive problem faced…

A Biophysics-based Protein Language Model for Protein Engineering

Videos

Cross Labs AI

UW-Madison

Transfer learning

Biology

Biophysics

Protein language models

Foundation models

LLM

Deep learning

Protein engineering

Simulations

We introduce Mutational Effect Transfer Learning (METL), a specialized protein language model that bridges the gap between traditional biophysics-based and machine learning approaches by incorporating synthetic data from molecular simulations.

Using Large Language Models for Meteorological Fact Finding

Videos

IT Prof

UW-Madison

LLM

Meteorology

This talk demonstrates harnessing the power of AI to open new avenues in data analysis, including for meteorological fact-finding. Discover how cutting-edge large language models (LLMs) like OpenAI’s ChatGPT 3.5 and 4.0 hold are poised to help the field of meteorological data analysis.

Trustworthy LLMs & Ethical AI

Videos

ML+X

UW-Madison

NLP

Text analysis

LLM

Deep learning

Trustworthy AI

DeTox

Ethical AI

Topic modeling

1. DeTox: Denoised Toxic Embeddings for Editing Model Toxicity — Rheeya Uppaal
2. A Project on AI Ethics — Mariab A. Knowles

Rheeya Uppaal, Mariah A. Knowles

Advancing Healthcare and Agriculture through Computer Vision

Videos

ML+X

UW-Madison

Computer vision

Ultrasound

Medical imaging

Athletics

Agriculture

LSTM

CNN-LSTM

CNN

Deep learning

1. An ultrasound-based method to measure knee kinematics enabled by deep learning — Matthew Blomquist
2. Plant breeding in the age of computer vision — Will de la Bretonne

Matthew Blomquist, Will de la Bretonne

Exploring Model Sharing in the Age of Foundation Models

Videos

ML+X

UW-Madison

Multimodal learning

Foundation models

Model sharing

Hugging Face

LLM

LMM

LLaVA

Deep learning

1. Model sharing and reproducible ML — Chris Endemann
2. LLaVA-NeXT and model sharing — Haotian Liu, PhD

Chris Endemann, Haotian Liu

Navigating Gravitational Waves with AI Insights

Videos

ML+X

UW-Madison

Physics

Simulations

Spectral analysis

Signal processing

1. Welcome and small group discussions — Chris Endemann
2. Classifying gravitational wave modes from core-collapse supernovae — Bella Finkel

Chris Endemann, Bella Finkel

Exploring Science Communication and Drug Synergy Analysis using GPT

Videos

ML+X

UW-Madison

Science communication

Healthcare

Drug synergy

LLM

Text mining

NLP

GPT for Science Communication: User-Interface and Developer Pipeline Approaches — Ben Rush, PhD

Advancing Biomedical Research with GPT-4: A Novel Approach to Drug Synergy…

Ben Rush, Jack Freeman

World Knowledge in the Time of Large Models

Videos

SILO

UW-Madison

VLM

LLM

LMM

Multimodal learning

Foundation models

This talk will discuss the massive shift that has come about in the vision and ML community as a result of the large pre-trained language and language and vision models such as Flamingo, GPT-4, and other models.

LLMS in Genomics and Health Coaching

Videos

ML+X

UW-Madison

Healthcare

Clustering

Deep learning

LLM

Genomics

1. Clustering of genomic sequences of mycoviruses using deep learning — Rohan Sontahlia
2. Spurring self-improvement and intrinsic motivation using LLMs and reinforcement learning — Michael Roytman

Rohan Sontahlia, Michael Roytman

LabelBench: A Framework for Benchmarking Label-Efficient Learning

Videos

MLOPT

UW-Madison

Active learning

Label-efficient learning

Active learning

Semi-supervised

ViT

Benchmarking

Labeled data are critical to modern machine learning applications, but obtaining labels can be expensive. To mitigate this cost, machine learning methods, such as transfer…

Time-Series Analysis

Videos

ML+X

UW-Madison

Time-series

Genomics

Biology

Healthcare

Computational Methods for Comparative Time Clocks in Early Development and Tissue Regeneration — Peng Jiang, PhD

Controlled Differential Equations on Long Sequences via…

Peng Jiang, Sourav Pal

Biomedical AI Research and Applications

Videos

UW-Madison

Exploring AI@UW

Biology

Healthcare

LLM

Computer vision

Multimodal learning

This session features lightning talks about biomedical applications of artificial intelligence from UW–Madison researchers working to develop algorithms and models to help…

Anthony Gitter, Junjie Hu, Yin Li, Anoop Mayampurath, Vikas Singh

Racism in AI

Videos

UW-Madison

Exploring AI@UW

Ethical AI

Bias

Fairness

Is artificial intelligence racist? In short, yes, it sure has been. But there’s more to the story. Lori Kido Lopez, UW–Madison professor and author of “Race and Digital Media”…

Lori Kido Lopez

Multimodal Learning

Videos

ML+X

UW-Madison

Multimodal learning

Deep learning

Computer vision

Healthcare

Genomics

Multimodal learning and analysis for understanding single-cell functional genomics in brains and brain diseases — Daifeng Wang, PhD

Transforming healthcare: AI-enhanced…

Daifeng Wang, Zachary Huemann, Pedro Morgado

Exploring Generative AI: An Introduction to Large Language Models and Diffusion Models

Videos

ML4MI

UW-Madison

LLM

VLM

LLaVA

LLM

GenAI

Diffusion

Deep learning

Multimodal learning

In this talk from the Machine Learning for Medical Imaging (ML4MI) community, Kangwook Lee, PhD, provides a comprehensive introduction to generative AI through the lens of…

AI and Medical Imaging

Videos

Exploring AI@UW

UW-Madison

Healthcare

Medical imaging

Image classification

Computer vision

Deep learning

Dr. Alan McMillan discusses the growing role of AI and machine learning in healthcare, particularly in radiology and medical imaging. He outlines how AI is being applied in…

Laurel Belman, Todd Shechter, Alan McMillan

AI in Action: Intelligent Systems and Business Operations

Videos

UW-Madison

Exploring AI@UW

AI & society

Business

Bias

Ethical AI

Laura Albert, professor and the David Gustafson Department Chair of Industrial & Systems Engineering at the UW–Madison College of Engineering discusses how artificial…

Unifying Audio-Visual Machine Perception – Tasks & Architectures

Videos

ML4MI

UW-Madison

Healthcare

Multimodal learning

Contrastive learning

Perception

Early-fusion

Autoencoder

Accurately recognizing, localizing, and separating sound sources is essential for effective audio-visual perception. Traditionally, these tasks have been approached…