neural_network.optimizers.adam_optimizer
========================================

.. py:module:: neural_network.optimizers.adam_optimizer

.. autoapi-nested-parse::

   Adam Optimizer

   Implements Adam (Adaptive Moment Estimation) for neural network training using NumPy.
   Adam combines momentum and adaptive learning rates using first and
   second moment estimates.

   Reference: https://arxiv.org/abs/1412.6980
   Author: Adhithya Laxman Ravi Shankar Geetha
   Date: 2025.10.21



Attributes
----------

.. autoapisummary::

   neural_network.optimizers.adam_optimizer.optimizer


Classes
-------

.. autoapisummary::

   neural_network.optimizers.adam_optimizer.Adam


Module Contents
---------------

.. py:class:: Adam(learning_rate: float = 0.001, beta1: float = 0.9, beta2: float = 0.999, epsilon: float = 1e-08)

   Adam optimizer.

   Combines momentum and RMSProp:
       m = beta1 * m + (1 - beta1) * gradient
       v = beta2 * v + (1 - beta2) * gradient^2
       m_hat = m / (1 - beta1^t)
       v_hat = v / (1 - beta2^t)
       param = param - learning_rate * m_hat / (sqrt(v_hat) + epsilon)


   .. py:method:: update(param_id: int, params: numpy.ndarray, gradients: numpy.ndarray) -> numpy.ndarray

      Update parameters using Adam.

      Args:
          param_id (int): Unique identifier for parameter group.
          params (np.ndarray): Current parameters.
          gradients (np.ndarray): Gradients of parameters.

      Returns:
          np.ndarray: Updated parameters.

      >>> optimizer = Adam(learning_rate=0.1)
      >>> params = np.array([1.0, 2.0])
      >>> grads = np.array([0.1, 0.2])
      >>> updated = optimizer.update(0, params, grads)
      >>> updated.shape
      (2,)



   .. py:attribute:: beta1
      :value: 0.9



   .. py:attribute:: beta2
      :value: 0.999



   .. py:attribute:: epsilon
      :value: 1e-08



   .. py:attribute:: learning_rate
      :value: 0.001



   .. py:attribute:: m
      :type:  dict[int, numpy.ndarray]


   .. py:attribute:: t
      :type:  dict[int, int]


   .. py:attribute:: v
      :type:  dict[int, numpy.ndarray]


.. py:data:: optimizer