Concept

Long short-term memory

Related lectures (32)

Language Modelling and Recurrent Neural Networks

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

Introduces Long Short-Term Memory (LSTM) networks as a solution to vanishing and exploding gradients in recurrent neural networks.

Recurrent Neural Networks: LSTMs & GRUs

Explores LSTM and GRU variants in recurrent neural networks, addressing challenges and advantages.

Recurrent Neural Networks: Training and Challenges

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

Deep Learning: Recurrent Neural Networks

Explores Recurrent Neural Networks for behavioral data, covering Deep Knowledge Tracing, LSTM, GRU networks, hyperparameter tuning, and time series prediction tasks.

Seq2Seq Models: Attention vs. No Attention

Explores Seq2Seq models with and without attention mechanisms, covering encoder-decoder architecture, context vectors, decoding processes, and different types of attention mechanisms.

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.

Ball-and-socket joint pose estimation

Focuses on ball-and-socket joint pose estimation using a magnetic field in an anthropomorphic design with artificial muscles and tendons.

Machine Translation: Attention Mechanism

Explores the attention mechanism in machine translation, addressing the bottleneck problem and improving NMT performance significantly.

Deep Learning for NLP

Explores deep learning for NLP, covering word embeddings, context representations, learning techniques, and challenges like vanishing gradients and ethical considerations.

Contextual Representations: ELMO and BERT Overview

Covers contextual representations in NLP, focusing on ELMO and BERT architectures and their applications in various tasks.

Feed-forward Networks

Introduces feed-forward networks, covering neural network structure, training, activation functions, and optimization, with applications in forecasting and finance.

Binary Sentiment Classifier Training

Covers the training of a binary sentiment classifier using an RNN.

Contextual Representations: ELMo & BERT

Explores the development of contextualized embeddings in NLP, focusing on ELMo and BERT's advancements and impact on NLP tasks.

Pre-Training: BiLSTM and Transformer

Delves into pre-training BiLSTM and Transformer models for NLP tasks, showcasing their effectiveness and applications.

Theoretical Properties of RNNs

Explores the theoretical properties and practical power of Recurrent Neural Networks, including their relationship to state machines and Turing completeness.

Deep Learning Techniques: Recurring Networks and LSTM Models

Discusses the implementation and optimization of recurring networks using LSTM models in deep learning.

Policy Gradient Evaluation: Example (1-step horizon)

Explores policy gradient evaluation with a 1-step horizon, update rules, comparisons with Perceptron and biology, and generalization techniques.

Part-of-Speech Tagging: Probabilistic Models

Explores Part-of-Speech tagging using probabilistic models like Hidden Markov Models and discusses the resolution of lexical ambiguities.