Lecture
Supervised Learning: Decision Trees
Related lectures (40)
Thermodynamics: Entropy and Ideal Gases
Explores entropy, ideal gases, and TDS equations in thermodynamics, emphasizing the importance of the Clausius inequality and the Carnot cycle.
Mutual Information: Continued
Explores mutual information for quantifying statistical dependence between variables and inferring probability distributions from data.
Information Measures: Estimation & Detection
Covers information measures, entropy, mutual information, and data processing inequality in signal representation.
Achievable Rate & Capacity
Explores achievable rate, channel capacity, spectral efficiency, and fading channels in wireless communication systems.
Decision Forests: Structure and Training
Covers decision forests, training, weak learners, entropy, boosting, 3D pose estimation, and practical applications.
Decision Trees: Induction and Pruning
Explores Decision Trees, from induction to pruning, emphasizing interpretability and automatic feature selection strengths, while addressing challenges like overfitting.
Entropy and Disorder
Explores entropy, disorder, and the calculation of maximum entropy under constraints using Lagrange multipliers.
Replica Symmetry Breaking: Full Solution & Condensation
Explores Replica Symmetry Breaking in the Random Energy Model, discussing configurational entropy and condensation.
Protein Residue Coevolution Analysis
Delves into analyzing residue coevolution in protein families to capture native contacts and predict spatial proximity and protein interactions.
Crowdsourcing: Classification Methodology
Explores crowdsourcing tasks distribution and aggregation algorithms for worker answers in classification methodology.