Lecture

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

Graph Chat

Chat with Graph Search

Ask any question about EPFL courses, lectures, exercises, research, news, etc. or try the example questions below.

DISCLAIMER: The Graph Chatbot is not programmed to provide explicit or categorical answers to your questions. Rather, it transforms your questions into API requests that are distributed across the various IT services officially administered by EPFL. Its purpose is solely to collect and recommend relevant references to content that you can explore to help you answer your questions.

Related lectures (64)

Non-Conceptual Knowledge Systems

Delves into the impact of deep learning on non-conceptual knowledge systems and the advancements in transformers and generative adversarial networks.

Non conceptual knowledge systems

Explores the impact of Deep learning on Digital Humanities, focusing on non conceptual knowledge systems and recent advancements in AI.

Neuroscience and AI: Bridging the Gap

Explores the gap between AI and human intelligence through neuroscience-inspired models and algorithms.

Image Processing II: Neural Networks and CNNs

Explores the evolution of CNNs in image processing, covering classical and deep neural networks, training algorithms, backpropagation, non-linear steps, loss functions, and software frameworks.

Generalization in Deep Learning

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

Convolutional Neural Networks

Introduces Convolutional Neural Networks (CNNs) for autonomous vehicles, covering architecture, applications, and regularization techniques.

Deep Neural Networks: Training and Optimization

Explores deep neural network training, optimization, preventing overfitting, and different network architectures.

Deep Learning for Question Answering

Explores deep learning for question answering, analyzing neural networks and model robustness to noise.

Machine Learning for Feature Extraction

Explores machine learning for feature extraction, 3D vision, and neural networks in mobile robotics.

Policy Gradient Methods in Reinforcement Learning

Covers policy gradient methods in reinforcement learning, focusing on optimization techniques and practical applications like the cartpole problem.

Deep Learning Agents: Reinforcement Learning

Explores Deep Learning Agents in Reinforcement Learning, emphasizing neural network approximations and challenges in training multiagent systems.

Bagging: Regularization Method in Deep Learning

Explores bagging as a regularization method in deep learning, training multiple model variants on different data subsets to improve generalization.

Deep Learning Paradigm

Explores the deep learning paradigm, including challenges, neural networks, robustness, fairness, interpretability, and energy efficiency.

Deep and Robust Reinforcement Learning Techniques

Discusses advanced reinforcement learning techniques, focusing on deep and robust methods, including actor-critic frameworks and adversarial learning strategies.

Understanding Deep Learning

Explores deep learning fundamentals, including image classification, neural network working principles, and machine learning challenges.

Policy Gradient Methods: Binary Actor Example

Introduces policy gradient methods using a simple example of a single neuron with binary output.

Tricks of the Trade in Deep Learning: Aims

Covers practical questions and aims in deep learning, including neuron types, network architecture, optimization, and weight initialization.

Feedforward Neural Networks: Activation Functions and Backpropagation

Introduces feedforward neural networks, activation functions, and backpropagation for training, addressing challenges and powerful methods.

Numerical analysis

Covers advanced numerical analysis topics including deep neural networks and optimization methods.

Deep Learning: Convolutional Networks

Explores convolutional neural networks, backpropagation, and stochastic gradient descent in deep learning.