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

Lecture

Improving Models of the Ventral Visual Pathway

Description

This lecture explores computational models of the ventral visual system, focusing on optimizing networks for performance on real-world challenging tasks, comparing to brain data, and discussing optimization strategies. It delves into the use of convolutional neural networks, hierarchical and retinotopic structures, and the importance of filter parameters. The lecture also covers the prediction of neural responses, the evaluation of learning rules, and the challenges of unsupervised learning. Additionally, it discusses the emergence of grid-like representations in artificial agents and the application of deep contrastive embeddings in neural predictivity. The lecture concludes with a discussion on the evaluation of learning rules from neural network observables and the implications of deep contrastive embeddings in improving ImageNet performance.

This video is available exclusively on Mediaspace for a restricted audience. Please log in to MediaSpace to access it if you have the necessary permissions.

Watch on Mediaspace

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.

Convolutional neural network

Convolutional neural network (CNN) is a regularized type of feed-forward neural network that learns feature engineering by itself via filters (or kernel) optimization. Vanishing gradients and exploding gradients, seen during backpropagation in earlier neural networks, are prevented by using regularized weights over fewer connections. For example, for each neuron in the fully-connected layer 10,000 weights would be required for processing an image sized 100 × 100 pixels.

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.

Types of artificial neural networks

There are many types of artificial neural networks (ANN). Artificial neural networks are computational models inspired by biological neural networks, and are used to approximate functions that are generally unknown. Particularly, they are inspired by the behaviour of neurons and the electrical signals they convey between input (such as from the eyes or nerve endings in the hand), processing, and output from the brain (such as reacting to light, touch, or heat). The way neurons semantically communicate is an area of ongoing research.

Feature learning

In machine learning, feature learning or representation learning is a set of techniques that allows a system to automatically discover the representations needed for feature detection or classification from raw data. This replaces manual feature engineering and allows a machine to both learn the features and use them to perform a specific task. Feature learning is motivated by the fact that machine learning tasks such as classification often require input that is mathematically and computationally convenient to process.

Related lectures (54)

Nonlinear Supervised Learning

Explores the inductive bias of different nonlinear supervised learning methods and the challenges of hyper-parameter tuning.

Deep Splines: Unifying Framework for Deep Neural Networks

Introduces a functional framework for deep neural networks with adaptive piecewise-linear splines, focusing on biomedical image reconstruction and the challenges of deep splines.

Supervised Learning Overview

Covers CNNs, RNNs, SVMs, and supervised learning methods, emphasizing the importance of tuning regularization and making informed decisions in machine learning.

Brain Intelligence: Continual Learning of Representational Models

Delves into the continual learning of representational models after deployment, highlighting the limitations of current artificial neural networks.

Splines and Machine Learning