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
- The concept of Machine Learning (ML)
- Why we need neural networks and deep learning?
- Selecting networks for different problems and data types
- Training and validating neural networks
- Comparing logistic regression to neural networks
- Neural Networks
- Biological inspirations for neural networks
- Neural Networks: Neurons, Perceptrons, and MLP (Multilayer Perceptron model)
- Training MLP: The backpropagation algorithm
- Activation functions: Linear, Sigmoid, Tanh, Softmax
- Loss functions for forecasting and classification
- Parameters: Learning rate, regularization, momentum
- Building Neural Networks in Python
- Evaluating neural network performance in Python
- Basics of Deep Networks
- What is deep learning?
- Architecture of Deep Networks: 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 Network (CNN)
- Recursive Neural Network
- Recurrent Neural Network (RNN)
- Overview of Libraries and Interfaces in Python
- Caffe
- Theano
- TensorFlow
- Keras
- MxNet
- Choosing the appropriate library for the problem
- Building Deep Networks in Python
- Choosing the appropriate architecture for a given problem
- Hybrid deep networks
- Training the network: Selecting the appropriate library and defining architecture
- Tuning the network: Initialization, activation functions, loss functions, optimization methods
- Avoiding overfitting: Detecting overfitting problems in deep networks, regularization
- Evaluating deep networks
- Case Studies in Python
- Image recognition using CNN
- Anomaly detection with Autoencoders
- Time series forecasting with RNN
- Dimensionality reduction using Autoencoders
- Classification using RBM
Requirements
Familiarity with machine learning, system architecture, and programming languages is desirable.
14 Hours
