Explainable Neural Networks

About
Privacy
Disclaimer

Graph Chatbot

Related lectures (31)

Page 2 of 4

Geometric Insights on Deep Learning Models

Delves into the geometric insights of deep learning models, exploring their vulnerability to perturbations and the importance of robustness and interpretability.

Statistical Approach: Summary and Quiz

Discusses statistical view of neural networks, classification tasks, and cross-entropy loss functions.

Multi-layer Neural Networks

Covers the fundamentals of multi-layer neural networks and the training process of fully connected networks with hidden layers.

Interpretable Machine Learning: Sparse Decision Trees and Interpretable Neural Networks

Explores the extremes of interpretability in machine learning, focusing on sparse decision trees and interpretable neural networks.

Projection Pursuit Regression: Nonlinear Modeling and Interpretability

Explores Projection Pursuit Regression for nonlinear modeling and the trade-offs with interpretability in neural networks.

Network Averaging: Theory and Applications

On network averaging covers labeled and unlabeled networks, statistical methods, challenges in network analysis, and practical considerations.

Neural Networks: Training and Optimization

Explores the training and optimization of neural networks, addressing challenges like non-convex loss functions and local minima.

Why are there so many saddle points?: Loss landscape and optimization methods

Explores the reasons behind the abundance of saddle points in deep learning optimization, emphasizing statistical and geometric arguments.

Generalization in Deep Learning

Delves into the trade-off between model complexity and risk, generalization bounds, and the dangers of overfitting complex function classes.

Kernel Methods: Neural Networks

Covers the fundamentals of neural networks, focusing on RBF kernels and SVM.