Artificial Neural Networks and Deep Learning: Loss landscape and optimization methods

Related lectures (32)

Page 3 of 4

Covers a crash course on deep learning, including the Mark I Perceptron, neural networks, optimization algorithms, and practical training aspects.

Discusses convolutional neural networks, their architecture, training techniques, and challenges like adversarial examples in deep learning.

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

Explores neural networks for regression and classification tasks, covering training, regularization, and practical examples.

Explores the historical development and training of multi-layered perceptrons, emphasizing the backpropagation algorithm and feature design.

Explores the regularized cross-entropy risk in neural networks, covering training processes and challenges in deep networks.

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

Explores neural network training, optimization, and environmental considerations, with insights into PCA and K-means clustering.

Explores data representations, histograms, neural networks, and deep learning concepts.

Explores learning in deep learning for autonomous vehicles, covering predictive models, RNN, ImageNet, and transfer learning.