ANN at its simplest (Deep Learning).pptx

I am here to explain ANN to understand in the fastest way possible.

1. Deep learning is a branch of artificial intelligence (AI). It is a method that teaches computers to process data in a way inspired by the human brain. Deep Learning Deep learning models can recognize complex pictures, text, sounds, and other data patterns to produce accurate insights and predictions. You can use deep learning methods to automate tasks that typically require human intelligence, such as describing images or transcribing a sound file into text. 

2. Automatic Feature Extraction: Learns features automatically from raw data. Scalability: Needs large datasets to perform well. Also performs better on larger dataset where machine learning may fail. Computation Power: Requires high computing power (GPU/TPU) Complexity: Excels at unstructured data (Images, Text, Audio, Video) How is it different from ML?

3. Algorithms in Deep Learning Types of Neural Networks: Feedforward Neural Networks (FNNs) Convolutional Neural Networks (CNNs) Recurrent Neural Networks (RNNs) Generative Adversial Networks (GANs) AutoEncoders Transformer Networks

4. Input Layer Takes the raw data (e.g., pixels, features). Hidden Layers Perform computations through weights, biases, and activation functions . Can be multiple layers (shallow vs. deep networks). Output Layer Produces the final prediction (e.g., classification result). Structure of ANN

5. Architecture of ANN

6. Architecture of ANN Every node (artificial neuron) has two main parts : Summation (Weighted Sum): - Each node receives multiple inputs. - Each input is multiplied by a weight (w) that represents its importance. - A bias (b) is added to shift the function This step is like “collecting all information” in a weighted manner.

7. Architecture of ANN Input Layer: The input layer is the first layer of an ANN where raw data enters the network. Each input is multiplied by a weight and added to a bias : The result is sent to the activation function in the hidden layer (e.g., ReLU , Sigmoid).

8. Architecture of ANN Hidden Layer: The hidden layer in an ANN is the layer(s) between the input layer and the output layer . It is called “hidden” because it is not directly visible to the outside world (we only see input and output). Hidden layers perform the actual computations and transformations on the input data.

9. Architecture of ANN Output Layer: The output layer is the final layer of an ANN that produces the network’s predictions or decisions after processing data through the input and hidden layers. It converts the learned features into a final result (class label, probability, numeric value, etc.).