This comprehensive course on Deep Learning is all about understanding and implementing models based on neural networks. Learn some basic concepts such as need and history of neural networks, gradient, forward propagation, loss functions and its implementation from scratch using python libraries. Understand the essential concepts of deep neural networks that collaborate with Google’s powerful library TensorFlow which comes with pre built Keras. We will dive deeper into the mathematics behind each of these concepts to understand them fully. In the end, conclude with a neural network model for classification using MNIST data set. Learn how the same concepts can be applied to business and real-life problems in other domains.
Skills covered
ANN
Tensorflow
Keras
Gradient
Backpropagation
Course Syllabus
Deep Learning with Python
Need for deep learning
Introduction to Tensorflow
Tensorflow :Eager execution and hello world
Tensorflow:Modelling an equation in Tensorflow
calculating loss and gradient
Hands On: Regression using tensorflow(Eager Execution and Eager Normalization)
Gradient
Keras framework
Classification using MNIST