Long short-term memory (LSTM) Courses and Certifications

StatQuest with Josh Starmer

Long Short-Term Memory (LSTM), Clearly Explained

Clear explanation of Long Short-Term Memory (LSTM) neural networks, their advantages over basic RNNs, and how they handle larger data sequences without gradient problems. Includes step-by-step breakdown of LSTM stages.

• YouTube
• 21 minutes
• Self-Paced
• Free Video

Time Series Forecasting with LSTMs

Master LSTM networks for time series forecasting by building, optimizing, and evaluating models that handle long-term dependencies effectively.

• CodeSignal
• 1 hour
• Self-Paced
• Free Certificate

Time Series Forecasting with LSTMs

Master LSTM networks for time series forecasting with PyTorch, building optimized models that handle long-term dependencies and evaluating performance using RMSE, MAE, and MAPE metrics.

• CodeSignal
• 1 hour
• Self-Paced
• Free Certificate

Krish Naik

LSTM Recurrent Neural Network In Depth Intuition

Gain in-depth intuition on LSTM Recurrent Neural Networks, exploring memory cells, operations, and layers for advanced understanding of this powerful deep learning architecture.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

Jeff Heaton

Programming LSTM with Keras and TensorFlow

1 rating

Explore LSTM and GRU layers for recurrent neural networks in Keras, laying the groundwork for NLP and time series prediction with practical examples and implementations.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

Venelin Valkov

LSTM Time Series Prediction Tutorial Using PyTorch in Python - Coronavirus Daily Cases Forecasting

Learn to forecast Coronavirus cases using LSTM and PyTorch. Covers data preprocessing, model building, training, evaluation, and future predictions with real-world time series data.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Alfredo Canziani

Recurrent Neural Networks, Vanilla and Gated - LSTM

Explore recurrent neural networks, including LSTM, covering architectures, training methods, and practical implementations using PyTorch for sequence-based tasks in deep learning.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video

Valerio Velardo - The Sound of AI

Long Short Term Memory Networks Explained Easily

Comprehensive explanation of LSTM networks, comparing them to simple RNNs and exploring their architecture and mathematical foundations for improved sequence learning.

• YouTube
• 28 minutes
• Self-Paced
• Free Video

StatQuest with Josh Starmer

Long Short-Term Memory with PyTorch + Lightning

Learn to implement and train LSTM networks using PyTorch and Lightning, covering custom LSTM coding, PyTorch's built-in LSTM, and advanced training techniques for deep learning projects.

• YouTube
• 33 minutes
• Self-Paced
• Free Video

Valerio Velardo - The Sound of AI

Melody Generation with RNN-LSTM

Master melody generation using Long Short-Term Memory networks to create AI-composed music from preprocessing datasets to converting neural network outputs into MIDI files.

• YouTube
• 4 hours 56 minutes
• Self-Paced
• Free Video

Credential

Deep Learning

147089 ratings at Coursera

Master neural networks, deep learning techniques, and their real-world applications. Build and optimize various architectures using Python and TensorFlow to tackle cutting-edge AI challenges in multiple domains.

• Coursera
• 12 weeks, 10 hours/week
• Self-Paced
• Paid Course
• 5 courses

AI Bites

XLSTM: Understanding Extended LSTMs with sLSTM and mLSTM Architecture

Delve into the evolution of LSTM networks, exploring how XLSTM's innovative sLSTM and mLSTM components enable parallel processing and compete with transformers in sequence-related tasks.

• YouTube
• 14 minutes
• Self-Paced
• Free Video

Discover AI

Matrix Long Short-Term Memory (mLSTM) - A New Alternative to Transformer LLMs

Explore the innovative xLSTM architecture and its matrix-based approach to neural networks, comparing its potential advantages over traditional transformer models in language processing.

• YouTube
• 23 minutes
• Self-Paced
• Free Video

tinyML

A Technique for Extreme Compression of LSTM Models

Explore extreme LSTM compression using sparse structured additive matrices. Learn doping techniques, co-matrix adaptation, and regularization for state-of-the-art accuracy at high compression factors in NLP applications.

• YouTube
• 53 minutes
• Self-Paced
• Free Video

Center for Language & Speech Processing(CLSP), JHU

Structure-Sensitive Dependency Learning in Recurrent Neural Networks - 2017

Explore RNNs' ability to learn structure-sensitive dependencies in language, focusing on English subject-verb agreement and comparing network performance to human errors.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video