Useful Links
Computer Science
Artificial Intelligence
Deep Learning
Deep Learning and Neural Networks
1. Foundations of Machine Learning and Neural Networks
2. Training Shallow Neural Networks
3. Deepening the Network
4. Practical Considerations for Training
5. Convolutional Neural Networks (CNNs)
6. Recurrent Neural Networks (RNNs)
7. The Transformer Architecture
8. Generative Models
9. Deep Reinforcement Learning
10. Advanced Topics and Specialized Architectures
11. Deployment and Production
Recurrent Neural Networks (RNNs)
Sequential Data Processing
Characteristics of Sequential Data
Temporal Dependencies
Variable-Length Sequences
Applications of Sequential Data
The Structure of RNNs
Recurrent Connections
Hidden State Concept
Mathematical Formulation
Unfolding Through Time
Computational Graphs for Sequences
Backpropagation Through Time (BPTT)
Types of RNN Architectures
One-to-One
One-to-Many
Many-to-One
Many-to-Many
Sequence-to-Sequence
Training RNNs
Backpropagation Through Time
Truncated BPTT
Gradient Flow in Time
Problems with Simple RNNs
Vanishing Gradient Problem
Exploding Gradient Problem
Short-Term Memory Limitations
Long-Term Dependencies Challenge
Long Short-Term Memory (LSTM) Networks
Motivation for LSTMs
LSTM Architecture
Cell State
Information Flow
Long-Term Memory Storage
Gate Mechanisms
Forget Gate
Function and Implementation
Selective Forgetting
Input Gate
Function and Implementation
Information Selection
Output Gate
Function and Implementation
Output Control
Candidate Values
Hidden State Updates
LSTM Variants
Peephole Connections
Coupled Forget and Input Gates
Gated Recurrent Units (GRUs)
Simplified Gated Architecture
GRU Components
Update Gate
Function and Implementation
Reset Gate
Function and Implementation
Candidate Hidden State
Comparison to LSTM
Parameter Efficiency
Performance Trade-offs
Advanced RNN Architectures
Bidirectional RNNs
Forward and Backward Processing
Information Integration
Deep RNNs
Stacked RNN Layers
Hierarchical Representations
Attention Mechanisms in RNNs
Attention Weights
Context Vectors
Applications of RNNs
Natural Language Processing
Language Modeling
Text Generation
Sentiment Analysis
Named Entity Recognition
Time-Series Forecasting
Stock Price Prediction
Weather Forecasting
Speech Recognition
Acoustic Modeling
Sequence Alignment
Machine Translation
Encoder-Decoder Architecture
Sequence-to-Sequence Models
Previous
5. Convolutional Neural Networks (CNNs)
Go to top
Next
7. The Transformer Architecture