Главная
Study mode:
on
You
History
Saved
In progress 0 courses
compleat 0 courses
#Art & Design #Adobe #ChatGPT #GitHub

#Interpretability

Showing: 53 courses
Stanford University

Explaining Model Decisions and Fixing Them Through Human Feedback

0 rewiews
Explore algorithms for explaining deep network decisions, building user trust, incorporating domain knowledge, learning grounded representations, and correcting unwanted biases in AI models.
Add to list
21 Lesons
58 minutes
On-Demand
Free-Video
Stanford University

Optimizing for Interpretability in Deep Neural Networks - Mike Wu

0 rewiews
Explore techniques for making deep neural networks more interpretable through regularization, focusing on medical applications in critical care and HIV treatment. Insights on balancing model performance with human-understandable decision processes.
Add to list
23 Lesons
51 minutes
On-Demand
Free-Video
Stanford University

Leveraging Social Theories to Enhance Human-AI Interaction

0 rewiews
Explores challenges in human-AI partnerships, focusing on interpretability tools' limitations and cognitive heuristics. Proposes incorporating social theories to improve decision-support systems and human-AI interaction.
Add to list
1 Lesons
55 minutes
On-Demand
Free-Video
University of Central Florida

Interpretable Explanations of Black Boxes by Meaningful Perturbation - CAP6412 Spring 2021

0 rewiews
Explore principles and methods for explaining black box functions in machine learning, focusing on image saliency, perturbation techniques, and meta-predictors for interpretable AI.
Add to list
23 Lesons
27 minutes
On-Demand
Free-Video
Simons Institute

Interpretability Agents: Automating and Scaling Model Interpretation

0 rewiews
Explore automated interpretability agents for scaling model interpretation, enabling efficient analysis of AI systems through hypothesis-driven experimentation and modular design.
Add to list
1 Lesons
42 minutes
On-Demand
Free-Video
Institute for Pure & Applied Mathematics (IPAM)

Interpretability for Deep Learning: Theory, Applications and Scientific Insights

0 rewiews
Dive into deep learning interpretability, exploring methods to enhance transparency, safety, and trustworthiness in AI deployment while uncovering scientific insights in various domains.
Add to list
1 Lesons
56 minutes
On-Demand
Free-Video
Microsoft

Live Responsible AI Dashboard: One-Stop Shop for Operationalizing RAI in Practice - Episode 43

0 rewiews
Explore the Responsible AI Dashboard, a comprehensive toolkit for ethical machine learning development. Learn about model debugging, fairness assessment, and responsible decision-making in AI systems.
Add to list
10 Lesons
27 minutes
On-Demand
Free-Video
Microsoft

Build Responsible AI Using Error Analysis Toolkit

0 rewiews
Explore Microsoft's Error Analysis toolkit for responsible AI, identifying model errors, diagnosing root causes, and building reliable solutions through interpretability, fairness, and debugging techniques.
Add to list
7 Lesons
26 minutes
On-Demand
Free-Video
Alan Turing Institute

Transparency in Algorithmic Decision-Making - Karen Yeung, Birmingham Law School

0 rewiews
Exploring transparency in algorithmic decision-making, focusing on legal, ethical, and social implications of AI and automated systems in light of GDPR implementation and its impact on data protection.
Add to list
14 Lesons
25 minutes
On-Demand
Free-Video
Alan Turing Institute

The GDPR and Beyond - Ideas from Academia and Policy Panel

0 rewiews
Exploring GDPR's impact on data protection, automated decision-making, and AI regulation. Experts discuss key concepts, implementation challenges, and future implications for governments and corporations.
Add to list
1 Lesons
36 minutes
On-Demand
Free-Video
Alan Turing Institute

The GDPR and Beyond - Elizabeth Denham, UK Information Commissioner

0 rewiews
Elizabeth Denham discusses GDPR implementation, its impact on data protection, and future implications for AI regulation. Insights from the UK's top data protection official on privacy, innovation, and accountability.
Add to list
1 Lesons
21 minutes
On-Demand
Free-Video
Alan Turing Institute

Machine Learning and Data Science for Medicine - A Vision, Some Progress and Opportunities

0 rewiews
Explore machine learning and data science applications in medicine, focusing on AutoPrognosis - an automated system for creating tailored, interpretable, and accurate prognostic models for various diseases.
Add to list
20 Lesons
46 minutes
On-Demand
Free-Video
Alan Turing Institute

Introduction to Data Ethics - Brent Mittelstadt

0 rewiews
Explore data ethics with Dr. Mittelstadt, covering algorithmic fairness, accountability, transparency, and privacy. Learn about ethical challenges in AI and data analytics, with real-world examples and regulatory insights.
Add to list
23 Lesons
1 hour 27 minutes
On-Demand
Free-Video
Alan Turing Institute

Be Prepared to Show Your Working! - Professor Sir David Spiegelhalter

0 rewiews
Explore algorithmic decision-making transparency, validation, and explainability with Professor Spiegelhalter. Learn about the importance of demonstrating trustworthiness and intelligent transparency in automated advice systems.
Add to list
36 Lesons
1 hour 10 minutes
On-Demand
Free-Video
Simons Institute

Towards Interpretable Data Science

0 rewiews
Explore holistic approaches to interpretable data science, focusing on counterfactual and attribution-based explanations for complex data processing and decision support systems.
Add to list
1 Lesons
35 minutes
On-Demand
Free-Video
Alan Turing Institute

Beyond Tech - Machine Learning in Science & Policy - Professor David Dunson, Duke

0 rewiews
Exploring machine learning applications beyond tech, highlighting challenges in science and policy. Discusses fair algorithms, interpretable models, and the need for targeted methods in complex domains.
Add to list
10 Lesons
58 minutes
On-Demand
Free-Video
Valence Labs

Interpretable Chirality-Aware Graph Neural Networks for QSAR Modeling in Drug Discovery

0 rewiews
Explore an innovative Graph Neural Network approach for drug discovery, incorporating molecular chirality and offering interpretable results to enhance quantitative structure-activity relationship modeling.
Add to list
13 Lesons
49 minutes
On-Demand
Free-Video
USC Information Sciences Institute

Pragmatic Interpretability - A Human-AI Cooperation Approach

0 rewiews
Explore pragmatic interpretability in machine learning, focusing on human-AI cooperation, selective explanations, and incorporating human intuition to enhance decision-making and model understanding.
Add to list
1 Lesons
53 minutes
On-Demand
Free-Video
ACM SIGPLAN

Using Logic Programming and Kernel-Grouping for Improving Interpretability of Convolutional Neural Networks

0 rewiews
Explore a neurosymbolic framework for improving CNN interpretability in image classification using logic programming and kernel-grouping techniques.
Add to list
1 Lesons
29 minutes
On-Demand
Free-Video
Yannic Kilcher

Neural Networks Are Decision Trees - With Alexander Mattick

0 rewiews
Exploring the equivalence between neural networks and decision trees, discussing interpretability, computational advantages, and potential collaborations between the two approaches.
Add to list
8 Lesons
32 minutes
On-Demand
Free-Video
Bolei Zhou

Understanding Deep Neural Networks - CVPR 2020 iMLCV Tutorial

0 rewiews
Explore deep neural network interpretability through meaningful perturbations, extremal perturbations, and activation analysis. Learn techniques for understanding and improving model behavior in computer vision tasks.
Add to list
29 Lesons
41 minutes
On-Demand
Free-Video
Graham Neubig

CMU Neural Nets for NLP: Model Interpretation

0 rewiews
Learn techniques for interpreting neural networks in NLP, including probing sentence embeddings, analyzing model behavior, and generating explanations for model decisions.
Add to list
13 Lesons
1 hour 4 minutes
On-Demand
Free-Video
Simons Institute

Formalizing Explanations of Neural Network Behaviors

0 rewiews
Explores strategies for formally explaining neural network behaviors, discussing alternatives to informal interpretations and rigorous proofs, aiming to provide safety benefits in AI research.
Add to list
1 Lesons
59 minutes
On-Demand
Free-Video
Simons Institute

Interpretability via Symbolic Distillation

0 rewiews
Explore symbolic distillation techniques for enhancing interpretability in large language models and transformers, focusing on practical applications and theoretical insights.
Add to list
1 Lesons
51 minutes
On-Demand
Free-Video
MITCBMM

Adversarial Examples and Human-ML Alignment

0 rewiews
Explore adversarial examples in machine learning, their impact on human-ML alignment, and strategies for improving model robustness and interpretability.
Add to list
18 Lesons
1 hour 1 minute
On-Demand
Free-Video
Simons Institute

Interpreting Deep Neural Networks

0 rewiews
Explore techniques for interpreting deep neural networks, focusing on methods to understand and explain their decision-making processes and internal representations.
Add to list
1 Lesons
47 minutes
On-Demand
Free-Video
Weights & Biases

How EleutherAI Trains and Releases LLMs - Interview with Stella Biderman

0 rewiews
Explore EleutherAI's approach to LLM development, covering model selection, training techniques, GPU choices, and interpretability challenges in this insightful interview with Stella Biderman.
Add to list
10 Lesons
1 hour 6 minutes
On-Demand
Free-Video
Open Data Science

Responsible AI Dashboard - A Tool for Operationalizing Responsible AI

0 rewiews
Explore Microsoft's Responsible AI Dashboard, an open-source framework integrating tools for error analysis, interpretability, fairness, and causal decision-making to build reliable and responsible AI products.
Add to list
16 Lesons
53 minutes
On-Demand
Free-Video
Open Data Science

Measuring Interpretability in AI - Transforming Black Box Systems into Transparent Tools

0 rewiews
Explore novel metrics for measuring AI interpretability in unsupervised and supervised methods, enhancing transparency in topic models and question-answering systems for broader applications.
Add to list
5 Lesons
41 minutes
On-Demand
Free-Video
Simons Institute

A Multimodal Automated Interpretability Agent - Understanding Lower-Level Intelligence

0 rewiews
Explore a multimodal AI agent for automated interpretability, bridging AI, psychology, and neuroscience to understand lower-level intelligence.
Add to list
1 Lesons
35 minutes
On-Demand
Free-Video
IMSA

The Rainbow Model of Neural Networks

0 rewiews
Exploring the Rainbow Model of Neural Networks: innovative approach to understanding and optimizing neural network architectures, enhancing AI performance and interpretability.
Add to list
1 Lesons
43 minutes
On-Demand
Free-Video
Computational Genomics Summer Institute CGSI

Less is More: Learning Signals to Learn Representations in Healthcare

0 rewiews
Explore advancements in machine learning for MRI reconstruction and medical imaging. Discover how less data can yield more accurate representations in healthcare applications.
Add to list
13 Lesons
40 minutes
On-Demand
Free-Video
Computational Genomics Summer Institute CGSI

Deep Generative Models in Medicine - CGSI 2023

0 rewiews
Explore deep generative models in medicine, covering robustness, interpretability, missing data, language models, and diffusion techniques for improved medical applications and research.
Add to list
23 Lesons
32 minutes
On-Demand
Free-Video
Computational Genomics Summer Institute CGSI

Interpretability and Out-of-Distribution Generalization in Deep Predictive Models

0 rewiews
Explore interpretability and out-of-distribution generalization in deep predictive models, focusing on nuisance-induced spurious correlations and real-time Shapley value estimation techniques.
Add to list
1 Lesons
41 minutes
On-Demand
Free-Video
Valence Labs

Uncovering and Inducing Interpretable Causal Structure in Deep Learning Models

0 rewiews
Explore causal abstraction theory for uncovering and inducing interpretable structures in deep learning models, focusing on faithful explanations and interventions during analysis and training.
Add to list
5 Lesons
56 minutes
On-Demand
Free-Video
AI Institute at UofSC - #AIISC

Knowledge-infused Learning for Autonomous Driving (KL4AD)

0 rewiews
Explore knowledge-infused learning techniques for autonomous driving, focusing on neuro-symbolic AI and its potential to enhance interpretability, explainability, and robustness in real-world applications.
Add to list
1 Lesons
1 hour 11 minutes
On-Demand
Free-Video
Association for Computing Machinery (ACM)

Explainability

0 rewiews
Explore cutting-edge research on explainable AI, including actionable recourse, model reconstruction, diverse explanations, and human-AI comparisons in deception detection.
Add to list
1 Lesons
50 minutes
On-Demand
Free-Video
Association for Computing Machinery (ACM)

Interpretable Active Learning

0 rewiews
Explore interpretable active learning techniques for machine learning models, focusing on transparency and understanding of model decisions in real-world applications.
Add to list
6 Lesons
21 minutes
On-Demand
Free-Video
Black Hat

Why Security Data Science Matters and How It's Different

0 rewiews
Explore security data science challenges and solutions, including machine learning for attack detection, threat intelligence, and malware analysis, with focus on overcoming unique security-specific obstacles.
Add to list
12 Lesons
52 minutes
On-Demand
Free-Video
GOTO Conferences

One Does Not Simply Put Machine Learning into Production

0 rewiews
Explore challenges and trade-offs in implementing machine learning in products, focusing on accuracy, cost, maintainability, and interpretability. Learn key considerations for successful ML integration.
Add to list
1 Lesons
37 minutes
On-Demand
Free-Video
WeAreDevelopers

Remaining Challenges in Deep Learning Based NLP

0 rewiews
Explores remaining challenges in Deep Learning-based NLP, including data limitations, performance metrics, robustness issues, representation problems, and lack of interpretability, despite recent advancements and media hype.
Add to list
14 Lesons
31 minutes
On-Demand
Free-Video
Toronto Machine Learning Series (TMLS)

Interpretability Tools as Feedback Loops in Machine Learning Training

0 rewiews
Explore machine learning interpretability techniques to optimize training sequences and develop more effective models without increasing compute or training time.
Add to list
1 Lesons
18 minutes
On-Demand
Free-Video
Toronto Machine Learning Series (TMLS)

Explainable Machine Learning in Finance - When Machines Surpass Human Intelligence

0 rewiews
Explore causal and counterfactual explainability in AI/ML models for finance, addressing challenges when machines surpass human intelligence in complex, high-risk applications.
Add to list
1 Lesons
35 minutes
On-Demand
Free-Video
GERAD Research Center

Operational Research for Fairness, Privacy and Interpretability in Machine Learning

0 rewiews
Explore responsible AI through operational research, focusing on fairness, interpretability, and privacy in machine learning. Learn to leverage Integer Linear Programming for optimal, fair rule lists.
Add to list
1 Lesons
45 minutes
On-Demand
Free-Video
USC Information Sciences Institute

Do Androids Know They're Only Dreaming of Electric Sheep?

0 rewiews
Explore transformer language models' internal representations to detect and analyze hallucinatory behavior in AI-generated content, with insights on task-dependent patterns and evaluation methods.
Add to list
1 Lesons
59 minutes
On-Demand
Free-Video
Center for Language & Speech Processing(CLSP), JHU

Deep Learning Interpretability and Explainability of Speech in a Clinical Context

0 rewiews
Explore deep learning interpretability and explainability of speech in clinical settings, focusing on advanced techniques and their practical applications.
Add to list
1 Lesons
54 minutes
On-Demand
Free-Video
Association for Computing Machinery (ACM)

Frontiers of Foundation Models for Time Series

0 rewiews
Explore foundation models for time series data, addressing challenges in science applications and discussing future research directions in deep learning for time series analysis.
Add to list
1 Lesons
36 minutes
On-Demand
Free-Video
MLOps.community

Seeing Like a Language Model - Understanding Embeddings and Meaning in AI

0 rewiews
Explore how language models process text and represent meaning through embeddings. Gain insights into building better retrieval-augmented LLM systems and designing natural interfaces for reading and writing.
Add to list
1 Lesons
34 minutes
On-Demand
Free-Video
Google TechTalks

Kolmogorov-Arnold Networks - Alternatives to Multi-Layer Perceptrons

0 rewiews
Explore Kolmogorov-Arnold Networks as alternatives to MLPs, offering improved accuracy and interpretability in data fitting and PDE solving. Discover their potential for scientific collaboration and law discovery.
Add to list
1 Lesons
52 minutes
On-Demand
Free-Video
Institut des Hautes Etudes Scientifiques (IHES)

Interpreting Deep Neural Networks Towards Trustworthiness

0 rewiews
Explore methods for interpreting neural networks, including contextual decomposition and adaptive wavelet distillation, to enhance model trustworthiness and performance.
Add to list
1 Lesons
33 minutes
On-Demand
Free-Video
Institut des Hautes Etudes Scientifiques (IHES)

Rapture of the Deep: Highs and Lows of Sparsity in Neural Networks

0 rewiews
Explore sparsity in neural networks, its role in interpretability, and innovative optimization techniques beyond gradient descent for learning fast transforms.
Add to list
14 Lesons
37 minutes
On-Demand
Free-Video
DataLearning@ICL

Interpretable and Structure-Preserving Data-Driven Methods for Physical Simulations

0 rewiews
Explore interpretable, structure-preserving data-driven methods for physical simulations. Discover techniques like DMD, LaSDI, and ROMs to accelerate and improve accuracy in various scientific applications.
Add to list
19 Lesons
51 minutes
On-Demand
Free-Video
Unify

Towards Monosemanticity: Decomposing Language Models with Dictionary Learning

0 rewiews
Explore monosemanticity in neural networks through sparse autoencoders. Learn how extracting interpretable features enhances understanding of language model behavior and improves reasoning capabilities.
Add to list
1 Lesons
1 hour 10 minutes
On-Demand
Free-Video