Lecture

Careful Cross-validation

In course

This course provides an overview and introduces modern methods for reinforcement learning (RL.) The course starts with the fundamentals of RL, such as Q-learning, and delves into commonly used approac

Description

This lecture covers the importance of careful cross-validation in deep neural networks, including the split of data into training, validation, and test sets, as well as the concept of K-fold cross-validation. The instructor explains the process of splitting the data and the significance of never touching the test data until the final evaluation. Examples using the MNIST dataset are provided to illustrate the practical implementation of careful cross-validation.

Instructors (2)

Wulfram Gerstner

Wulfram Gerstner is Director of the Laboratory of Computational Neuroscience LCN at the EPFL. His research in computational neuroscience concentrates on models of spiking neurons and spike-timing dependent plasticity, on the problem of neuronal coding in single neurons and populations, as well as on the link between biologically plausible learning rules and behavioral manifestations of learning. He teaches courses for Physicists, Computer Scientists, Mathematicians, and Life Scientists at the EPFL. After studies of Physics in Tübingen and at the Ludwig-Maximilians-University Munich (Master 1989), Wulfram Gerstner spent a year as a visiting researcher in Berkeley. He received his PhD in theoretical physics from the Technical University Munich in 1993 with a thesis on associative memory and dynamics in networks of spiking neurons. After short postdoctoral stays at Brandeis University and the Technical University of Munich, he joined the EPFL in 1996 as assistant professor. Promoted to Associate Professor with tenure in February 2001, he is since August 2006 a full professor with double appointment in the School of Computer and Communication Sciences and the School of Life Sciences. Wulfram Gerstner has been invited speaker at numerous international conferences and workshops. He has served on the editorial board of the Journal of Neuroscience, Network: Computation in Neural Systems', Journal of Computational Neuroscience', and `Science'.

Caglar Gulcehre

Official source

Related lectures (32)

Model Evaluation

Explores underfitting, overfitting, hyperparameters, bias-variance trade-off, and model evaluation in machine learning.

Deep Learning: Designing Neural Network Models

Covers the design and optimization of neural network models in deep learning.

Neural Networks: Training and Activation

Explores neural networks, activation functions, backpropagation, and PyTorch implementation.

Model Assessment and Hyperparameter Tuning

Explores model assessment, hyperparameter tuning, and resampling strategies in machine learning.

Document Analysis: Topic Modeling

Explores document analysis, topic modeling, and generative models for data generation in machine learning.