Media Summary: Bio: Vitali Petsiuk is a 2nd-year Computer Science Ph.D. student advised by Professor Kate Saenko at Boston University. He does ... Lecture 14 from BENG 212 at UCSD and corresponding to Chapter 14 from Systems Biology: Constraint-based Reconstruction ... How do Convolutional Neural Network see? How does AI utilize the information from the images to make predictions?

Rise Randomized Input Sampling For - Detailed Analysis & Overview

Bio: Vitali Petsiuk is a 2nd-year Computer Science Ph.D. student advised by Professor Kate Saenko at Boston University. He does ... Lecture 14 from BENG 212 at UCSD and corresponding to Chapter 14 from Systems Biology: Constraint-based Reconstruction ... How do Convolutional Neural Network see? How does AI utilize the information from the images to make predictions? Shapley values - Occlusion sensitivity maps - Spectral clustering - This video is part of an online course, Intro to Artificial Intelligence. Check out the course here: ... Learn more about watsonx: Neural networks reflect the behavior of the human brain, allowing computer ...

The talk will focus on two important perturbation methods of Explainable AI (XAI):

Photo Gallery

RISE: Randomized Input Sampling for Explanation of Black-box Models  (AI Paper Summary)
RISE (randomized input sampling for explanation of black box models)
MIC 2018 - RISE: Randomized Input Sampling for Explanation of Black-box Models
Lecture 14. Randomized Sampling
READ AI WITH ME - RISE (PETSIUK ET AL., 2018)
Explainable machine learning (2022, 4th lecture): Local model-agnostic methods
Black-box explanation of object detectors via saliency maps (CVPR 21 Oral)
Resampling - Artificial Intelligence for Robotics
Applied Deep Learning 2021 - Lecture 11 - Explainable AI
Applied Deep Learning 2023 - Lecture 12 - Explainable AI
Applied Deep Learning 2025 - Lecture 10 - Explainable AI
Neural Networks Explained in 5 minutes
View Detailed Profile
RISE: Randomized Input Sampling for Explanation of Black-box Models  (AI Paper Summary)

RISE: Randomized Input Sampling for Explanation of Black-box Models (AI Paper Summary)

RISE

RISE (randomized input sampling for explanation of black box models)

RISE (randomized input sampling for explanation of black box models)

Paper:

MIC 2018 - RISE: Randomized Input Sampling for Explanation of Black-box Models

MIC 2018 - RISE: Randomized Input Sampling for Explanation of Black-box Models

Bio: Vitali Petsiuk is a 2nd-year Computer Science Ph.D. student advised by Professor Kate Saenko at Boston University. He does ...

Lecture 14. Randomized Sampling

Lecture 14. Randomized Sampling

Lecture 14 from BENG 212 at UCSD and corresponding to Chapter 14 from Systems Biology: Constraint-based Reconstruction ...

READ AI WITH ME - RISE (PETSIUK ET AL., 2018)

READ AI WITH ME - RISE (PETSIUK ET AL., 2018)

How do Convolutional Neural Network see? How does AI utilize the information from the images to make predictions?

Explainable machine learning (2022, 4th lecture): Local model-agnostic methods

Explainable machine learning (2022, 4th lecture): Local model-agnostic methods

Shapley values - Occlusion sensitivity maps - Spectral clustering -

Black-box explanation of object detectors via saliency maps (CVPR 21 Oral)

Black-box explanation of object detectors via saliency maps (CVPR 21 Oral)

https://cs-people.bu.edu/vpetsiuk/drise/

Resampling - Artificial Intelligence for Robotics

Resampling - Artificial Intelligence for Robotics

This video is part of an online course, Intro to Artificial Intelligence. Check out the course here: ...

Applied Deep Learning 2021 - Lecture 11 - Explainable AI

Applied Deep Learning 2021 - Lecture 11 - Explainable AI

Petsiuk et al.,

Applied Deep Learning 2023 - Lecture 12 - Explainable AI

Applied Deep Learning 2023 - Lecture 12 - Explainable AI

Petsiuk et al.,

Applied Deep Learning 2025 - Lecture 10 - Explainable AI

Applied Deep Learning 2025 - Lecture 10 - Explainable AI

Petsiuk et al.,

Neural Networks Explained in 5 minutes

Neural Networks Explained in 5 minutes

Learn more about watsonx: https://ibm.biz/BdvxRs Neural networks reflect the behavior of the human brain, allowing computer ...

XAI Tutorial 2023 | Perturbation based explanations | Sehyun Lee

XAI Tutorial 2023 | Perturbation based explanations | Sehyun Lee

The talk will focus on two important perturbation methods of Explainable AI (XAI):