Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
- Overview of Neural Networks and Deep Learning
- Understanding the concept of Machine Learning (ML)
- Rationale for using neural networks and deep learning
- Selecting appropriate networks for various problems and data types
- Training and validating neural networks
- Comparing logistic regression with neural networks
- Neural Networks
- Biological inspiration for neural networks
- Neural networks: Neurons, Perceptrons, and MLPs (Multilayer Perceptron models)
- Training MLPs using the backpropagation algorithm
- Activation functions: linear, sigmoid, Tanh, Softmax
- Loss functions suitable for forecasting and classification
- Parameters: learning rate, regularization, momentum
- Constructing neural networks in Python
- Evaluating the performance of neural networks in Python
- Fundamentals of Deep Networks
- What is deep learning?
- Deep network architecture: Parameters, Layers, Activation Functions, Loss Functions, Solvers
- Restricted Boltzmann Machines (RBMs)
- Autoencoders
- Deep Network Architectures
- Deep Belief Networks (DBN) – architecture and applications
- Autoencoders
- Restricted Boltzmann Machines
- Convolutional Neural Networks
- Recursive Neural Networks
- Recurrent Neural Networks
- Overview of Python Libraries and Interfaces
- Caffe
- Theano
- TensorFlow
- Keras
- MXNet
- Selecting the appropriate library for a specific problem
- Building Deep Networks in Python
- Choosing the right architecture for a given problem
- Hybrid deep networks
- Network training – selecting the appropriate library and defining the architecture
- Network tuning – initialization, activation functions, loss functions, optimization methods
- Avoiding overfitting – identifying overfitting issues in deep networks and applying regularization
- Evaluating deep networks
- Case Studies in Python
- Image recognition using CNNs
- Anomaly detection with Autoencoders
- Time series forecasting with RNNs
- Dimensionality reduction using Autoencoders
- Classification using RBMs
Requirements
Familiarity with machine learning, system architecture, and programming languages is recommended.
14 Hours
Testimonials (1)
The training was organized and well-planned out, and I come out of it with systematized knowledge and a good look at topics we looked at
