Lesson 1 Flashcards
Neurons
The basic unit of a neural network, analogous to the human brain’s neurons. Each neuron receives input, processes it, and passes the output to the next layer.
Layers:
Input layer
The first layer that receives the input data.
Layers:
Hidden Layers
Layers between the input and output layers where computations are performed. There can be one or many hidden layers, depending on the network’s depth.
Layers:
Output Layer
The final layer that produces the output of the network.
Working of Neural Networks
Weight and Biases
Each connection between neurons has a weight, and each neuron has a bias. These parameters are adjusted during the training process to minimize the error in the network’s predictions.
Working of Neural Networks:
Activation Function
Determines the output of a neuron given a set of inputs and weights. Common activation functions include sigmoid, tanh, and ReLU (Rectified Linear Unit).
Working of Neural Networks:
Forward Propagation
The process of passing input data through the network to get the output.
Working of Neural Networks:
Backpropagation
A method used during training to update the weights and biases to minimize the error. It involves computing the gradient of the loss function and adjusting weights in the opposite direction of the gradient.
Applications of Neural Networks:
Neural networks are used in a variety of applications, including: Speech Recognition
Identifying objects in images and understanding spoken language.
Applications of Neural Networks:
Neural networks are used in a variety of applications, including: Natural Language Processing (NLP)
Tasks such as translation, sentiment analysis, and text generation.
Applications of Neural Networks:
Neural networks are used in a variety of applications, including: Recommendation System
Suggesting products, movies, or music based on user preferences.
Key Concepts:
Training data
The data used to train the neural network. It includes input data and the corresponding correct output.
Key Concepts:
Epochs
One complete pass through the entire training dataset.
Key Concepts:
Loss function
Measures how well the neural network’s predictions match the actual outcomes. The goal is to minimize this loss.
Key Concepts:
Learning Rate
A hyperparameter that controls how much to change the model in response to the estimated error each time the model weights are updated.