RNN Architecture Components:

• Hidden State: $h_t$ - Memory that carries information from previous timesteps
• Input Weight: $W_{input}$ - How much the current input affects the hidden state
• Hidden Weight: $W_{hidden}$ - How much the previous hidden state influences the current one
• Bias: Constant term added to the computation
• Activation Function: Non-linear transformation (tanh, ReLU, sigmoid)

RNN Formula:
$h_t=f(W_{input}\cdot x_t+W_{hidden}\cdot h_{t-1}+bias)$

Where $f$ is the activation function, $x_t$ is the input at time $t$, and $h_{t-1}$ is the previous hidden state.

How to Use:

• Select a sequence from the dropdown to see different patterns (Fibonacci, linear, etc.)
• Adjust weights to see how they affect hidden state evolution
• Try different activation functions to understand their impact on processing
• Use "Step Forward" to manually process each timestep
• Watch the visualization to see how information flows through the network

Sequence Types:
• Fibonacci: Each number is sum of previous two
• Linear: Simple counting sequence
• Alternating: Pattern that switches between values
• Exponential: Powers of 2 sequence
• Sine Pattern: Smooth oscillating values

Understanding RNN Behavior:

• Input Weight ($W_{input}$): Higher values make current input more influential
• Hidden Weight ($W_{hidden}$): Higher values give more importance to memory
• Activation Functions:
- Tanh: Outputs between -1 and 1, good for centered data
- ReLU: Only positive outputs, can cause exploding gradients
- Sigmoid: Outputs between 0 and 1, can suffer from vanishing gradients

Observing Patterns:
• Memory Effect: See how previous inputs influence current outputs
• Weight Impact: Notice how different weights change the sequence processing
• Activation Choice: Different functions handle the same sequence differently