4.49 (99 Ratings)

This comprehensive course on ‘Artificial Intelligence’ covers all the basics of neural network-based models. Get a conceptual understanding of learning mechanisms such as Need and history of neural networks, gradient, forward propagation, loss functions and its implementation using python libraries. Learn some essential concepts related to deep neural networks that also work with Google’s powerful library Tensorflow which comes with pre built Keras. We will be covering all theoretical and practical aspects of this subject, in-depth. Dive deeper into the mathematics behind each concept to understand their specifics. We will conclude with a neural network model for classification using MNIST data set. Learn its application on business or real-life problems in other domains.

#### Skills covered

- Perceptron
- ANN
- Gradient
- Backpropagation
- Activation Functions
- Softmax Function

## Course Syllabus

#### Artificial Intelligence with Python

- History behind neural networks
- Relationship between biological neuron and artificial neuron
- Perceptron and working mechanism
- Architecture of artificial neural network
- Types of activation functions
- Softmax function
- Forward propagation
- Loss function
- Demo using keras framework
- Back propagation and gradient descent
- Tensorflow 2.0
- Demo on MNIST data set