{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "header",
   "metadata": {},
   "source": [
    "# Training Recurrent Neural Networks: Integrator Task\n",
    "\n",
    "This tutorial demonstrates how to train a recurrent neural network (RNN) to perform an **integration task** - a fundamental computation in neuroscience where networks must accumulate evidence over time.\n",
    "\n",
    "## Learning Objectives\n",
    "\n",
    "By the end of this tutorial, you will:\n",
    "- Understand the integration task and its importance\n",
    "- Build custom RNN cells in BrainState\n",
    "- Train RNNs on temporal tasks\n",
    "- Use trainable initial states\n",
    "- Apply L2 regularization to prevent overfitting\n",
    "- Visualize RNN predictions on time-series data\n",
    "\n",
    "## The Integration Task\n",
    "\n",
    "**Goal**: Given a noisy input signal, the network must compute the cumulative sum (integral) over time.\n",
    "\n",
    "```\n",
    "Input:  [x₁, x₂, x₃, ...]\n",
    "Output: [x₁, x₁+x₂, x₁+x₂+x₃, ...]\n",
    "```\n",
    "\n",
    "This task requires:\n",
    "- **Memory**: Remember past inputs\n",
    "- **Accumulation**: Continuously integrate information\n",
    "- **Robustness**: Handle noise in inputs\n",
    "\n",
    "**Applications**:\n",
    "- Evidence accumulation in decision-making\n",
    "- Position estimation from velocity\n",
    "- Financial modeling (cumulative returns)\n",
    "- Signal processing"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "setup",
   "metadata": {},
   "source": [
    "## Setup and Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "imports",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:07.603916Z",
     "start_time": "2025-10-11T09:58:04.111801Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:18.054370Z",
     "iopub.status.busy": "2026-05-30T17:38:18.054132Z",
     "iopub.status.idle": "2026-05-30T17:38:22.773861Z",
     "shell.execute_reply": "2026-05-30T17:38:22.772875Z"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "An NVIDIA GPU may be present on this machine, but a CUDA-enabled jaxlib is not installed. Falling back to cpu.\n"
     ]
    }
   ],
   "source": [
    "from typing import Callable\n",
    "\n",
    "import jax\n",
    "import jax.numpy as jnp\n",
    "import matplotlib.pyplot as plt\n",
    "import numpy as np\n",
    "\n",
    "import brainstate\n",
    "import braintools\n",
    "\n",
    "# Set random seeds\n",
    "np.random.seed(42)\n",
    "brainstate.random.seed(42)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "config",
   "metadata": {},
   "source": [
    "## Configuration"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "hyperparams",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:07.614207Z",
     "start_time": "2025-10-11T09:58:07.608297Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:22.776586Z",
     "iopub.status.busy": "2026-05-30T17:38:22.776062Z",
     "iopub.status.idle": "2026-05-30T17:38:22.780906Z",
     "shell.execute_reply": "2026-05-30T17:38:22.780165Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Configuration:\n",
      "  Sequence length: 25 steps\n",
      "  Batch size: 512\n",
      "  Hidden units: 100\n",
      "  Training batches: 2500\n"
     ]
    }
   ],
   "source": [
    "# Task parameters\n",
    "dt = 0.04              # Time step\n",
    "num_step = int(1.0 / dt)  # Steps per trial (25 steps for 1.0 time unit)\n",
    "num_batch = 512        # Batch size\n",
    "\n",
    "# Network parameters\n",
    "num_hidden = 100       # Hidden units in RNN\n",
    "\n",
    "# Training parameters\n",
    "learning_rate = 0.025\n",
    "lr_decay_rate = 0.99975\n",
    "l2_reg = 2e-4\n",
    "num_epochs = 5\n",
    "batches_per_epoch = 500\n",
    "\n",
    "print(f\"Configuration:\")\n",
    "print(f\"  Sequence length: {num_step} steps\")\n",
    "print(f\"  Batch size: {num_batch}\")\n",
    "print(f\"  Hidden units: {num_hidden}\")\n",
    "print(f\"  Training batches: {num_epochs * batches_per_epoch}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "data_section",
   "metadata": {},
   "source": [
    "## Generate Data\n",
    "\n",
    "### Data Generation Function\n",
    "\n",
    "We'll create random walk inputs and compute their cumulative sums as targets:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "data_gen",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:07.623573Z",
     "start_time": "2025-10-11T09:58:07.619211Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:22.782758Z",
     "iopub.status.busy": "2026-05-30T17:38:22.782617Z",
     "iopub.status.idle": "2026-05-30T17:38:22.786677Z",
     "shell.execute_reply": "2026-05-30T17:38:22.785816Z"
    }
   },
   "outputs": [],
   "source": [
    "@brainstate.transform.jit(static_argnums=2)\n",
    "def build_inputs_and_targets(mean=0.025, scale=0.01, batch_size=10):\n",
    "    \"\"\"Generate integration task data.\n",
    "    \n",
    "    Args:\n",
    "        mean: Mean of the random walk bias\n",
    "        scale: Standard deviation of noise\n",
    "        batch_size: Number of sequences\n",
    "        \n",
    "    Returns:\n",
    "        inputs: [num_step, batch_size, 1] - Input sequences\n",
    "        targets: [num_step, batch_size, 1] - Target cumulative sums\n",
    "    \"\"\"\n",
    "    # Create initial bias\n",
    "    sample = brainstate.random.normal(size=(1, batch_size, 1))\n",
    "    bias = mean * 2.0 * (sample - 0.5)\n",
    "    \n",
    "    # Generate white noise\n",
    "    samples = brainstate.random.normal(size=(num_step, batch_size, 1))\n",
    "    noise_t = scale / dt ** 0.5 * samples\n",
    "    \n",
    "    # Inputs = bias + noise\n",
    "    inputs = bias + noise_t\n",
    "    \n",
    "    # Targets = cumulative sum of inputs\n",
    "    targets = jnp.cumsum(inputs, axis=0)\n",
    "    \n",
    "    return inputs, targets\n",
    "\n",
    "\n",
    "def train_data():\n",
    "    \"\"\"Generator for training data.\"\"\"\n",
    "    for _ in range(batches_per_epoch * num_epochs):\n",
    "        yield build_inputs_and_targets(0.025, 0.01, num_batch)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "visualize_data",
   "metadata": {},
   "source": [
    "### Visualize Sample Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "plot_data",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:08.124430Z",
     "start_time": "2025-10-11T09:58:07.634037Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:22.788570Z",
     "iopub.status.busy": "2026-05-30T17:38:22.788335Z",
     "iopub.status.idle": "2026-05-30T17:38:23.373535Z",
     "shell.execute_reply": "2026-05-30T17:38:23.372747Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1400x400 with 2 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Generate one batch for visualization\n",
    "sample_inputs, sample_targets = build_inputs_and_targets(0.025, 0.01, 3)\n",
    "\n",
    "fig, axes = plt.subplots(1, 2, figsize=(14, 4))\n",
    "\n",
    "# Plot inputs\n",
    "for i in range(3):\n",
    "    axes[0].plot(sample_inputs[:, i, 0], alpha=0.7, label=f'Sample {i+1}')\n",
    "axes[0].set_xlabel('Time Step')\n",
    "axes[0].set_ylabel('Input Value')\n",
    "axes[0].set_title('Input Sequences (Random Walks)', fontweight='bold')\n",
    "axes[0].legend()\n",
    "axes[0].grid(True, alpha=0.3)\n",
    "\n",
    "# Plot targets\n",
    "for i in range(3):\n",
    "    axes[1].plot(sample_targets[:, i, 0], alpha=0.7, label=f'Sample {i+1}')\n",
    "axes[1].set_xlabel('Time Step')\n",
    "axes[1].set_ylabel('Cumulative Sum')\n",
    "axes[1].set_title('Target Sequences (Integrals)', fontweight='bold')\n",
    "axes[1].legend()\n",
    "axes[1].grid(True, alpha=0.3)\n",
    "\n",
    "plt.tight_layout()\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "model_section",
   "metadata": {},
   "source": [
    "## Building the RNN\n",
    "\n",
    "### Custom RNN Cell\n",
    "\n",
    "We'll create a vanilla RNN cell with optional trainable initial state:"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "rnn_cell",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:08.146616Z",
     "start_time": "2025-10-11T09:58:08.139758Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:23.375625Z",
     "iopub.status.busy": "2026-05-30T17:38:23.375394Z",
     "iopub.status.idle": "2026-05-30T17:38:23.382488Z",
     "shell.execute_reply": "2026-05-30T17:38:23.381141Z"
    }
   },
   "outputs": [],
   "source": [
    "class RNNCell(brainstate.nn.Module):\n",
    "    \"\"\"Vanilla RNN cell with trainable weights.\n",
    "    \n",
    "    h_t = activation(W_combined @ [x_t; h_{t-1}] + b)\n",
    "    \"\"\"\n",
    "    \n",
    "    def __init__(\n",
    "        self,\n",
    "        num_in: int,\n",
    "        num_out: int,\n",
    "        state_initializer: Callable = braintools.init.ZeroInit(),\n",
    "        w_initializer: Callable = braintools.init.XavierNormal(),\n",
    "        b_initializer: Callable = braintools.init.ZeroInit(),\n",
    "        activation: Callable = brainstate.nn.relu,\n",
    "        train_state: bool = False,  # Whether to train initial state\n",
    "    ):\n",
    "        super().__init__()\n",
    "        \n",
    "        self.num_out = num_out\n",
    "        self.train_state = train_state\n",
    "        \n",
    "        # Activation function\n",
    "        self.activation = activation\n",
    "        \n",
    "        # Combined weight matrix [input; hidden] -> hidden\n",
    "        W = braintools.init.param(\n",
    "            w_initializer, \n",
    "            (num_in + num_out, num_out)\n",
    "        )\n",
    "        b = braintools.init.param(b_initializer, (num_out,))\n",
    "        \n",
    "        self.W = brainstate.ParamState(W)\n",
    "        self.b = brainstate.ParamState(b) if b is not None else None\n",
    "        \n",
    "        # Trainable initial state (optional)\n",
    "        if train_state:\n",
    "            self.state2train = brainstate.ParamState(\n",
    "                braintools.init.ZeroInit()(num_out)\n",
    "            )\n",
    "        \n",
    "        self._state_initializer = state_initializer\n",
    "    \n",
    "    def init_state(self, batch_size=None, **kwargs):\n",
    "        \"\"\"Initialize hidden state.\"\"\"\n",
    "        self.state = brainstate.HiddenState(\n",
    "            braintools.init.param(\n",
    "                self._state_initializer, \n",
    "                (self.num_out,), \n",
    "                batch_size\n",
    "            )\n",
    "        )\n",
    "        \n",
    "        # Use trainable initial state if specified\n",
    "        if self.train_state:\n",
    "            self.state.value = jnp.repeat(\n",
    "                jnp.expand_dims(self.state2train.value, axis=0), \n",
    "                batch_size, \n",
    "                axis=0\n",
    "            )\n",
    "    \n",
    "    def update(self, x):\n",
    "        \"\"\"Update RNN cell for one time step.\n",
    "        \n",
    "        Args:\n",
    "            x: Input [batch, input_dim]\n",
    "            \n",
    "        Returns:\n",
    "            h: New hidden state [batch, hidden_dim]\n",
    "        \"\"\"\n",
    "        # Concatenate input and previous hidden state\n",
    "        x_combined = jnp.concatenate([x, self.state.value], axis=-1)\n",
    "        \n",
    "        # Linear transformation\n",
    "        h = x_combined @ self.W.value\n",
    "        if self.b is not None:\n",
    "            h += self.b.value\n",
    "        \n",
    "        # Apply activation\n",
    "        h = self.activation(h)\n",
    "        \n",
    "        # Update state\n",
    "        self.state.value = h\n",
    "        \n",
    "        return h"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "network_section",
   "metadata": {},
   "source": [
    "### Complete RNN Network"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "rnn_network",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:08.157911Z",
     "start_time": "2025-10-11T09:58:08.153554Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:23.385203Z",
     "iopub.status.busy": "2026-05-30T17:38:23.384930Z",
     "iopub.status.idle": "2026-05-30T17:38:23.388789Z",
     "shell.execute_reply": "2026-05-30T17:38:23.388083Z"
    }
   },
   "outputs": [],
   "source": [
    "class RNN(brainstate.nn.Module):\n",
    "    \"\"\"RNN with recurrent layer and linear output.\"\"\"\n",
    "    \n",
    "    def __init__(self, num_in, num_hidden):\n",
    "        super().__init__()\n",
    "        \n",
    "        # RNN layer with trainable initial state\n",
    "        self.rnn = RNNCell(num_in, num_hidden, train_state=True)\n",
    "        \n",
    "        # Output projection\n",
    "        self.out = brainstate.nn.Linear(num_hidden, 1)\n",
    "    \n",
    "    def update(self, x):\n",
    "        \"\"\"Process one time step.\n",
    "        \n",
    "        Args:\n",
    "            x: Input at current time step\n",
    "            \n",
    "        Returns:\n",
    "            output: Prediction at current time step\n",
    "        \"\"\"\n",
    "        # RNN forward pass using >> operator (pipe)\n",
    "        return x >> self.rnn >> self.out"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "create_model",
   "metadata": {},
   "source": [
    "### Create Model and Optimizer"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "instantiate",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:41.775272Z",
     "start_time": "2025-10-11T09:58:41.742833Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:23.391501Z",
     "iopub.status.busy": "2026-05-30T17:38:23.391240Z",
     "iopub.status.idle": "2026-05-30T17:38:27.971915Z",
     "shell.execute_reply": "2026-05-30T17:38:27.971137Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+------------------------+------------+\n",
      "|        Modules         | Parameters |\n",
      "+------------------------+------------+\n",
      "|   ('out', 'weight')    |    101     |\n",
      "|      ('rnn', 'W')      |   10.10K   |\n",
      "|      ('rnn', 'b')      |    100     |\n",
      "| ('rnn', 'state2train') |    100     |\n",
      "|         Total          |   10.40K   |\n",
      "+------------------------+------------+\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "10401"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Create RNN model\n",
    "model = RNN(num_in=1, num_hidden=num_hidden)\n",
    "\n",
    "# Get trainable parameters\n",
    "weights = model.states(brainstate.ParamState)\n",
    "\n",
    "# Create optimizer with learning rate decay\n",
    "lr_schedule = braintools.optim.ExponentialDecayLR(\n",
    "    learning_rate,\n",
    "    decay_steps=1, \n",
    "    decay_rate=lr_decay_rate\n",
    ")\n",
    "optimizer = braintools.optim.Adam(lr=lr_schedule, eps=1e-1)\n",
    "optimizer.register_trainable_weights(weights)\n",
    "\n",
    "brainstate.nn.count_parameters(model)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "training_section",
   "metadata": {},
   "source": [
    "## Training the RNN\n",
    "\n",
    "### Define Prediction and Loss Functions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "id": "functions",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:46.850437Z",
     "start_time": "2025-10-11T09:58:46.846157Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:27.973844Z",
     "iopub.status.busy": "2026-05-30T17:38:27.973472Z",
     "iopub.status.idle": "2026-05-30T17:38:27.978249Z",
     "shell.execute_reply": "2026-05-30T17:38:27.977364Z"
    }
   },
   "outputs": [],
   "source": [
    "@brainstate.transform.jit\n",
    "def f_predict(inputs):\n",
    "    \"\"\"Make predictions for a sequence.\n",
    "    \n",
    "    Args:\n",
    "        inputs: [num_steps, batch_size, 1]\n",
    "        \n",
    "    Returns:\n",
    "        predictions: [num_steps, batch_size, 1]\n",
    "    \"\"\"\n",
    "    # Initialize RNN state\n",
    "    brainstate.nn.init_all_states(model, batch_size=inputs.shape[1])\n",
    "    \n",
    "    # Process sequence\n",
    "    return brainstate.transform.for_loop(model.update, inputs)\n",
    "\n",
    "\n",
    "def f_loss(inputs, targets, l2_reg=2e-4):\n",
    "    \"\"\"Compute loss with L2 regularization.\n",
    "    \n",
    "    Args:\n",
    "        inputs: Input sequences\n",
    "        targets: Target sequences\n",
    "        l2_reg: L2 regularization coefficient\n",
    "        \n",
    "    Returns:\n",
    "        loss: Total loss value\n",
    "    \"\"\"\n",
    "    # Get predictions\n",
    "    predictions = f_predict(inputs)\n",
    "    \n",
    "    # Mean squared error\n",
    "    mse = braintools.metric.squared_error(predictions, targets).mean()\n",
    "    \n",
    "    # L2 regularization on weights\n",
    "    l2 = 0.0\n",
    "    for weight in weights.values():\n",
    "        for leaf in jax.tree.leaves(weight.value):\n",
    "            l2 += jnp.sum(leaf ** 2)\n",
    "    \n",
    "    return mse + l2_reg * l2"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "train_step_section",
   "metadata": {},
   "source": [
    "### Define Training Step"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "train_step",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T09:58:50.380060Z",
     "start_time": "2025-10-11T09:58:50.376128Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:27.980841Z",
     "iopub.status.busy": "2026-05-30T17:38:27.980470Z",
     "iopub.status.idle": "2026-05-30T17:38:27.985524Z",
     "shell.execute_reply": "2026-05-30T17:38:27.984752Z"
    }
   },
   "outputs": [],
   "source": [
    "@brainstate.transform.jit\n",
    "def f_train(inputs, targets):\n",
    "    \"\"\"Perform one training step.\n",
    "    \n",
    "    Args:\n",
    "        inputs: Input sequences\n",
    "        targets: Target sequences\n",
    "        \n",
    "    Returns:\n",
    "        loss: Loss value\n",
    "    \"\"\"\n",
    "    # Compute gradients\n",
    "    grads, loss = brainstate.transform.grad(\n",
    "        f_loss, \n",
    "        weights, \n",
    "        return_value=True\n",
    "    )(inputs, targets)\n",
    "    \n",
    "    # Update parameters\n",
    "    optimizer.update(grads)\n",
    "    \n",
    "    return loss"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "run_training",
   "metadata": {},
   "source": [
    "### Run Training Loop"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "training_loop",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T10:00:05.708106Z",
     "start_time": "2025-10-11T09:58:51.844330Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:38:27.987489Z",
     "iopub.status.busy": "2026-05-30T17:38:27.987268Z",
     "iopub.status.idle": "2026-05-30T17:39:07.527168Z",
     "shell.execute_reply": "2026-05-30T17:39:07.526068Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Starting training...\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0, Batch 100, Loss 0.19359\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0, Batch 200, Loss 0.02319\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0, Batch 300, Loss 0.02118\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0, Batch 400, Loss 0.05296\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0, Batch 500, Loss 0.04366\n",
      "\n",
      "Epoch 0 completed: Avg Loss = 0.06692\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Batch 100, Loss 0.02038\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Batch 200, Loss 0.01986\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Batch 300, Loss 0.01943\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Batch 400, Loss 0.01905\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1, Batch 500, Loss 0.01868\n",
      "\n",
      "Epoch 1 completed: Avg Loss = 0.01948\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2, Batch 100, Loss 0.01833\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2, Batch 200, Loss 0.01799\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2, Batch 300, Loss 0.01766\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2, Batch 400, Loss 0.01733\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 2, Batch 500, Loss 0.01702\n",
      "\n",
      "Epoch 2 completed: Avg Loss = 0.01767\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3, Batch 100, Loss 0.01670\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3, Batch 200, Loss 0.01640\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3, Batch 300, Loss 0.01609\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3, Batch 400, Loss 0.01580\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 3, Batch 500, Loss 0.01552\n",
      "\n",
      "Epoch 3 completed: Avg Loss = 0.01610\n",
      "\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4, Batch 100, Loss 0.01523\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4, Batch 200, Loss 0.01496\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4, Batch 300, Loss 0.01469\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4, Batch 400, Loss 0.01442\n"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 4, Batch 500, Loss 0.01416\n",
      "\n",
      "Epoch 4 completed: Avg Loss = 0.01469\n",
      "\n",
      "Training complete!\n"
     ]
    }
   ],
   "source": [
    "print(\"Starting training...\\n\")\n",
    "\n",
    "for i_epoch in range(num_epochs):\n",
    "    epoch_losses = []\n",
    "    \n",
    "    for i_batch, (inputs, targets) in enumerate(train_data()):\n",
    "        if i_batch >= batches_per_epoch:\n",
    "            break\n",
    "        \n",
    "        loss = f_train(inputs, targets)\n",
    "        epoch_losses.append(float(loss))\n",
    "        \n",
    "        if (i_batch + 1) % 100 == 0:\n",
    "            avg_loss = np.mean(epoch_losses[-100:])\n",
    "            print(f'Epoch {i_epoch}, Batch {i_batch + 1:3d}, Loss {avg_loss:.5f}')\n",
    "    \n",
    "    avg_epoch_loss = np.mean(epoch_losses)\n",
    "    print(f'\\nEpoch {i_epoch} completed: Avg Loss = {avg_epoch_loss:.5f}\\n')\n",
    "\n",
    "print(\"Training complete!\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "eval_section",
   "metadata": {},
   "source": [
    "## Evaluation and Visualization\n",
    "\n",
    "### Test on New Data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "evaluation",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T10:00:06.068883Z",
     "start_time": "2025-10-11T10:00:05.724537Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:39:07.529703Z",
     "iopub.status.busy": "2026-05-30T17:39:07.529419Z",
     "iopub.status.idle": "2026-05-30T17:39:08.000971Z",
     "shell.execute_reply": "2026-05-30T17:39:08.000007Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test data generated:\n",
      "  Input shape: (25, 1, 1)\n",
      "  Target shape: (25, 1, 1)\n",
      "  Prediction shape: (25, 1, 1)\n"
     ]
    }
   ],
   "source": [
    "# Generate test data\n",
    "brainstate.nn.init_all_states(model, 1)\n",
    "x_test, y_test = build_inputs_and_targets(0.025, 0.01, 1)\n",
    "predictions = f_predict(x_test)\n",
    "\n",
    "print(f\"Test data generated:\")\n",
    "print(f\"  Input shape: {x_test.shape}\")\n",
    "print(f\"  Target shape: {y_test.shape}\")\n",
    "print(f\"  Prediction shape: {predictions.shape}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "plot_results",
   "metadata": {},
   "source": [
    "### Plot Predictions vs. Ground Truth"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "visualization",
   "metadata": {
    "ExecuteTime": {
     "end_time": "2025-10-11T10:00:06.213455Z",
     "start_time": "2025-10-11T10:00:06.073378Z"
    },
    "execution": {
     "iopub.execute_input": "2026-05-30T17:39:08.004469Z",
     "iopub.status.busy": "2026-05-30T17:39:08.003346Z",
     "iopub.status.idle": "2026-05-30T17:39:08.135051Z",
     "shell.execute_reply": "2026-05-30T17:39:08.134339Z"
    }
   },
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 1200x500 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Test MSE: 0.000007\n"
     ]
    }
   ],
   "source": [
    "plt.figure(figsize=(12, 5))\n",
    "\n",
    "# Convert to numpy for plotting\n",
    "y_true = np.asarray(y_test[:, 0]).flatten()\n",
    "y_pred = np.asarray(predictions[:, 0]).flatten()\n",
    "time_steps = np.arange(len(y_true))\n",
    "\n",
    "# Plot ground truth and predictions\n",
    "plt.plot(time_steps, y_true, 'b-', linewidth=2, label='Ground Truth', alpha=0.7)\n",
    "plt.plot(time_steps, y_pred, 'r--', linewidth=2, label='RNN Prediction', alpha=0.7)\n",
    "\n",
    "plt.xlabel('Time Step', fontsize=12)\n",
    "plt.ylabel('Cumulative Value', fontsize=12)\n",
    "plt.title('RNN Integration Task Performance', fontsize=14, fontweight='bold')\n",
    "plt.legend(fontsize=11)\n",
    "plt.grid(True, alpha=0.3)\n",
    "plt.tight_layout()\n",
    "plt.show()\n",
    "\n",
    "# Compute final error\n",
    "mse = np.mean((y_true - y_pred) ** 2)\n",
    "print(f\"\\nTest MSE: {mse:.6f}\")"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Ecosystem-py",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.13.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}