Mediaspace scheduled maintenance: Aug 25, 2026 07:00 - 12:00 AM. During this time, videos will be temporarily unavailable. Check status updates.

Lecture

Neural Networks Optimization

In course

CIVIL-459: Deep learning for autonomous vehicles

Deep Learning (DL) is the subset of Machine learning reshaping the future of transportation and mobility. In this class, we will show how DL can be used to teach autonomous vehicles to detect objects, make predictions, and make decisions. (Fun fact: this s ...

Description

This lecture covers tips and tricks for neural networks optimization, focusing on backpropagation with examples, batch normalization, weight initialization, and hyperparameter search strategies. It also discusses the importance of data preprocessing, model architecture design, loss functions, and regularization. The instructor emphasizes the use of transfer learning, model ensembles, and pretrained networks to improve performance. Additionally, the lecture explores the implementation of neural networks, including forward/backward APIs, training procedures, and monitoring techniques.

Instructor

Alexandre Massoud Alahi

Alexandre Alahi is currently an Assistant Professor at EPFL. He spent five years at Stanford University as a Post-doc and Research Scientist after obtaining his Ph.D. from EPFL. His research enables machines to perceive the world and make decisions in the context of transportation problems and smart environments. He has worked on the theoretical challenges and practical applications of socially-aware Artificial Intelligence, i.e., systems equipped with perception and social intelligence. He was awarded the Swiss NSF early and advanced researcher grants for his work on predicting human social behavior. He won the CVPR Open Source Award (2012) for his work on Retina-inspired image descriptors, and the ICDSC Challenge Prize (2009) for his sparsity-driven algorithm that has tracked more than 100 million pedestrians to date. His research has been covered internationally by BBC, abc, PBS, Euronews, Wall street journal, and other national news outlets around the world. Alexandre has also co-founded multiple startups such as Visiosafe, and won several startup competitions. He was elected as one of the Top 20 Swiss Venture leaders in 2010.

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

Artificial neural network

Artificial neural networks (ANNs, also shortened to neural networks (NNs) or neural nets) are a branch of machine learning models that are built using principles of neuronal organization discovered by connectionism in the biological neural networks constituting animal brains. An ANN is based on a collection of connected units or nodes called artificial neurons, which loosely model the neurons in a biological brain. Each connection, like the synapses in a biological brain, can transmit a signal to other neurons.

Feedforward neural network

A feedforward neural network (FNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. Its flow is uni-directional, meaning that the information in the model flows in only one direction—forward—from the input nodes, through the hidden nodes (if any) and to the output nodes, without any cycles or loops, in contrast to recurrent neural networks, which have a bi-directional flow.

Regularization (mathematics)

In mathematics, statistics, finance, computer science, particularly in machine learning and inverse problems, regularization is a process that changes the result answer to be "simpler". It is often used to obtain results for ill-posed problems or to prevent overfitting. Although regularization procedures can be divided in many ways, the following delineation is particularly helpful: Explicit regularization is regularization whenever one explicitly adds a term to the optimization problem.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Backpropagation

As a machine-learning algorithm, backpropagation performs a backward pass to adjust the model's parameters, aiming to minimize the mean squared error (MSE). In a single-layered network, backpropagation uses the following steps: Traverse through the network from the input to the output by computing the hidden layers' output and the output layer. (the feedforward step) In the output layer, calculate the derivative of the cost function with respect to the input and the hidden layers.

Related lectures (42)

Neural Networks: Training and Activation

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

Deep Learning: Convolutional Neural Networks

Covers Convolutional Neural Networks, standard architectures, training techniques, and adversarial examples in deep learning.

Perception: Data-Driven Approaches

Explores perception in deep learning for autonomous vehicles, covering image classification, optimization methods, and the role of representation in machine learning.

The Hidden Convex Optimization Landscape of Deep Neural Networks

Explores the hidden convex optimization landscape of deep neural networks, showcasing the transition from non-convex to convex models.

Multilayer Perceptron: Training and Optimization