Duration
Artificial Neural Network
3 days
What you'll learn
In this course on artificial intelligence, participants will be provided an overview of AI, and explained on how it can be used for an effective and efficient decision making for an organization. The course will be a mixture of engaging short lectures with examples and use cases to help participants know about Tensorflow, spark and Deep learning in the exciting field of Artificial Intelligence.
Who this course is for
- Data Engineers
- Data Scientists
- Machine Learning Engineers
- Integration Engineers
- Architects
Prerequisites
Participants should preferably have some hands-on experience on Python
Course Outline
Introduction to Deep Learning
- Introduction to Machine Learning?
- What is Deep Learning?
- Relationship between Deep Learning and Machine Learning
- Deep Learning Use cases
- Concepts and Terms
- How to implement Deep Learning?
- Various Libraries, Pros & Cons
Artificial Neural Network
- Introduction to Neural Networks
- The Neuron
- Introduction to Perceptron
- The Activation Function
- Neural Network Activation Functions
- Basic Neural Nets
- Concepts
- Gradient Descent
- Stochastic Gradient Descent
TensorFlow
- What is TensorFlow?
- Installing TensorFlow
- TensorFlow Graphs
- Variables and Placeholders
- Activation Functions
Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN)
- CNN History
- Understanding CNNs
- CNN Application
- Introduction to Optimization
- Hyperparameter tuning
- Regularization
- Recurrent Neural Networks (RNNs)
- Application of RNNs
Modern Architecture
- Understand modern architectures of RNNs: LSTM, GRU
Programme scope, delivery arrangements and suitability are confirmed during enquiry.