DSA ADS Course - 2021
Discuss neurosymbolic AI systems with logical reasoning and explainability via symbolic knowledge representation. Consider trust, safety, interpretability and accountability of AI.
Neurosymbolic AI: The 3rd Wave - 2020
Abstract
September, 2021
One Hundred Year Study on Artificial Intelligence (AI100) 2021 Study Panel Report
September 2021
Abstract
September, 2021
Highlights
• Cortical neurons are well approximated by a deep neural network (DNN) with 5–8 layers
• DNN’s depth arises from the interaction between NMDA receptors and dendritic morphology
• Dendritic branches can be conceptualized as a set of spatiotemporal pattern detectors
• We provide a unified method to assess the computational complexity of any neuron type
Summary
DSA ADS Course - 2021
Machine Learning, Foundation Models, Artificial Intelligence, Risk Management
DSA ADS Course - 2021
Causal Data Science, Machine Learning, Individual-level Optimal Causal Interventions, Causal Models
Discuss statistical causal inference methods.
Estimating individual-level optimal causal interventions combining causal models and machine learning models - 2021
Abstract
DSA ADS Course - 2021
Causal Data Science, Causal Inference, Linguistic Causation, CausaLM, Causal Model Explanation, Counterfactual Language Models, Machine Learning
Discuss causative linguistic expressions and causal model explanation through counterfactual language models.
CausaLM: Causal Model Explanation Through Counterfactual Language Models - 2021
Abstract
DSA ADS Course - 2021
DoWhy, Causal Assumptions, Causal Inference, Causal Data Science, Machine Learning
Discuss successful application of causal inference techniques. As computing systems are more frequently and more actively intervening in societally critical domains such as healthcare, education, and governance, it is critical to correctly predict and understand the causal effects of these interventions. Without an A/B test, conventional machine learning methods, built on pattern recognition and correlational analyses, are insufficient for decision-making.
DSA ADS Course - 2021
Machine Learning, Causality, Causal Models, Knowledge Representation
Discuss “data fitting” vs “data interpreting” approaches to data science along three dimensions: Expediency, Transparency, and Explainability.
Radical Empiricism and Machine Learning Research - May, 2021 by Judea Pearl
Abstract
DSA ADS Course - 2021
Causality, Causal Reasoning, Causal Inference, Machine Learning, Algorithms
Discuss causality and machine learning - contrast with statistical correlations.
The Seven Tools of Causal Inference, with Reflections on Machine Learning - March, 2019 By Judea Pearl