This course on Bank Defaulters using Artificial Neural Networks (ANN) aims to teach learners about ANN architecture, weights, biases, activation functions, back propagation, and more. The course covers principles such as ANN Architecture, Weights, Biasis, Activation Functions, Back Propagation, and demonstrates these concepts with examples. By the end of the course, learners will have a good understanding of how ANNs work and how to apply them in real-world scenarios. The course uses a combination of theoretical explanations and practical demonstrations to help learners grasp the concepts effectively. This course is suitable for individuals interested in understanding and working with artificial neural networks, particularly in the context of identifying bank defaulters.
Overview
Syllabus
Course Introduction.
Objective of the course.
Architecture of ANN.
Weights , Biasis and Activation Functions.
Activation Function.
Loss Functions in Neural Networks.
Back Propagation in Neural Networks.
Gradient Descent.
Keras_Basic_ANN_Architecture - Demo.
Dataset Overview and Model Framework.
ANN_Application_Credit_Data - Demo.
Taught by
Great Learning
