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

Lecture

Recurrent Neural Networks: LSTMs & GRUs

Description

This lecture covers the continuation of recurrent neural networks with multiple layers and bidirectionality, focusing on LSTM and GRU variants. It discusses the challenges of learning long-range dependencies, the use of gates in GRUs, and the advantages of LSTMs and GRUs over traditional RNNs. The instructor explains the concepts through practical examples and addresses issues like vanishing gradients and optimal architectures for different tasks.

Official source

Ontological neighbourhood

Information engineering

Machine learning: Artificial neural networks

Related concepts (32)

Long short-term memory

Long short-term memory (LSTM) network is a recurrent neural network (RNN), aimed to deal with the vanishing gradient problem present in traditional RNNs. Its relative insensitivity to gap length is its advantage over other RNNs, hidden Markov models and other sequence learning methods. It aims to provide a short-term memory for RNN that can last thousands of timesteps, thus "long short-term memory".

Vanishing gradient problem

In machine learning, the vanishing gradient problem is encountered when training artificial neural networks with gradient-based learning methods and backpropagation. In such methods, during each iteration of training each of the neural networks weights receives an update proportional to the partial derivative of the error function with respect to the current weight. The problem is that in some cases, the gradient will be vanishingly small, effectively preventing the weight from changing its value.

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.

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.

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.

Related lectures (32)

Recurrent Neural Networks: Training and Challenges

Discusses recurrent neural networks, their training challenges, and solutions like LSTMs and GRUs.

Language Modelling and Recurrent Neural Networks

Explores language modelling, RNNs, n-gram models, LSTMs, and bidirectional RNNs.

Sequence to Sequence Models: Overview and Applications

Covers sequence to sequence models, their architecture, applications, and the role of attention mechanisms in improving performance.

Recurrent Neural Networks: Neural Language Models

Explores fixed-context neural language models, RNNs, vanishing gradients, and sequence labeling in NLP.

Feedforward Neural Networks: Activation Functions and Backpropagation