Convolutional Neural Network

Tensor based CNN

Edux implements a Tensor based CNN, read this article to understand what a Tensor is. Tensor

Layers

• InputLayer
• ConvolutionalLayer
• PoolingLayer
• DropoutLayer
• DenseLayer (Fully Connected Layer)
• BatchNormalizationLayer
• ActivationLayer

Optimizer

• Edux supports various optimization algorithms for training its Tensor-based CNN, including:
  • Stochastic Gradient Descent (SGD)
  • Adam
  • RMSprop
  • And more. The choice of optimizer can significantly affect the training speed and convergence of the neural network.

Loss Functions

• In Edux, you can choose from a range of loss functions for your Tensor-based CNN, including:
  • Mean Squared Error (MSE): For regression tasks
  • Cross-Entropy: For classification tasks
  • And more. These loss functions quantify the difference between the predicted outputs and the actual labels during training.

Activation Functions

• Activation functions determine the output of a neuron in a neural network. Edux provides support for various activation functions, including:
  • ReLU (Rectified Linear Unit)
  • Sigmoid
  • Tanh
  • And more. The choice of activation function can impact the network's ability to model complex relationships within the data.