Covers Multilayer Perceptrons, artificial neurons, activation functions, matrix notation, flexibility, regularization, regression, and classification tasks.
Explores analog-to-digital conversion, neural signal optimization, multichannel architectures, and on-chip compression techniques in neuroengineering.
Covers the training process of a neural network, including feedforward, cost function, gradient checking, and visualization of hidden layers.
Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.
Explores neural networks convergence through parameter fitting and alternating regret, with a focus on the NeurIPS 2023 event at EPFL.
Explores neural quantum states and their representation using artificial neural networks.
