Arficial Neural Network that is topic of network subject

it is topic of network in BSCS

1. Artificial Neural Networks (ANN) Lecture 30-Artificial Neural Networks 1

2. Outline Introduction Biological Neurons Model of ANN Activation Function Sigmoid Activation Function Threshold Function Lecture 30-Artificial Neural Networks 2

3. Lecture 30-Artificial Neural Networks 3 Introduction The most intelligent device- “Human Brain.” The machine that revolutionized the whole world- “Computer.” Inefficiencies of the computer has lead to the evolution of “Artificial Neural Network.”

4. Lecture 30-Artificial Neural Networks 4 ANN Introduction Neural networks are parallel computing devices, which are basically an attempt to make a computer model of the brain. Artificial Neural Network (ANN) is an efficient computing system whose central theme is borrowed from the analogy of biological neural networks. ANNs are also named as “artificial neural systems,” or “parallel distributed processing systems,” or “connectionist systems or connectionism .” The main objective is to develop a system to perform various computational tasks faster than the traditional systems.

5. Biological Neuron A nerve cell neuron is a special biological cell that processes information. According to an estimation, there are huge number of neurons, approximately 10 11 with numerous interconnections, or approximately 10 15 . Lecture 30-Artificial Neural Networks 5

6. Model of ANN For the above general model of artificial neural network, the net input can be calculated as follows − y in =x 1 .w 1 +x 2 .w 2 +x 3 .w 3 … x m .w m i.e., Net input y in =∑ mi x i .w i Lecture 30-Artificial Neural Networks 6

7. Lecture 30-Artificial Neural Networks 7 ANN Cont’d The output can be calculated by applying the activation function over the net input. Y=F(yin) Biological Neural Network Artificial Neural Network Dendrites Inputs Cell nucleus Nodes Synapse Weights Axon Output

8. Lecture 30-Artificial Neural Networks 8 Activation Function Activation functions determine the output of a deep learning model, its accuracy, and the computational efficiency of training a model Activation functions are mathematical equations that determine the output of a neural network. The function is attached to each neuron in the network, and determines whether it should be activated (“ fired ”) or not. Activation functions also help normalize the output of each neuron to a range between and 1 or between -1 and 1.

9. Sigmoid Activation Function This activation function performs input editing between and 1. It is positive in nature. It is always bounded which means its output cannot be less than 0 and more than 1. It is also strictly increasing in nature which means more the input higher would be the output. It can be defined as The sigmoid function is used when the model is predicting probability. used to approximate output from the actual net input. Lecture 30-Artificial Neural Networks 9

10. Sigmoid Activation Function Lecture 30-Artificial Neural Networks 10

11. Threshold Function The threshold function is used when you don’t want to worry about the uncertainty in the middle. Threshold function decides whether to fire a neuron or not. It is applied to the value of sigmoid function. 1, if x>=0.50 0, if x < 0.50 Lecture 30-Artificial Neural Networks 11

12. ANN Layers Input Layer: As the name suggests, it accepts inputs in several different formats provided by the programmer. Hidden Layer: The hidden layer presents in-between input and output layers. It performs all the calculations to find hidden features and patterns. Output Layer: The input goes through a series of transformations using the hidden layer, which finally results in output that is conveyed using this layer.

13. Lecture 30-Artificial Neural Networks 13 Bias The bias neuron is a special neuron added to each layer in the neural network, which simply stores the value of 1. Without a bias neuron, each neuron takes the input and multiplies it by a weight, with nothing else added to the equation. So, for example, it is not possible to input a value of and output 2. Although neural networks can work without bias neurons, in reality, they are almost always added.

14. Bias Lecture 30-Artificial Neural Networks 14

15. Types of Artificial Neural Networks There are two Artificial Neural Network topologies Feed Forward and Feedback. 1.FeedBack ANN Here, feedback loops are allowed. They are used in content addressable memories.

16. Feedback ANN Feedback Feedback

17. Lecture 30-Artificial Neural Networks 17 2- Feed-Forward Network There is no feedback loop means the signal can only flow in one direction from input to output. It can be divided into the following two types − Single Layer Perceptron Multi-Layer Perceptron

18. Single Layer Perceptron The concept is of feed-forward ANN having only one weighted layer. In Single Layer Perceptron input layer is directly connected to the output layer. Lecture 30-Artificial Neural Networks 18

19. Multi-Layer Perceptron The concept is of feed-forward ANN having more than one weighted layer. As this network has one or more layers between the input and the output layer, it is called hidden layer. Lecture 30-Artificial Neural Networks 19

20. Lecture 30-Artificial Neural Networks 20 Applications Neural networks can perform the following tasks: Translate text Identify faces Recognize speech Read handwritten text Control robots And a lot more

21. End