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 do we need neural networks and deep learning?
- Selecting appropriate networks for different problems and data types
- Training and validating neural networks
- Comparing logistic regression with neural networks
- Neural networks
- Biological inspirations behind neural networks
- Neural Networks – Neuron, Perceptron, and MLP (Multilayer Perceptron model)
- Learning MLP – the backpropagation algorithm
- Activation functions – linear, sigmoid, Tanh, Softmax
- Loss functions suitable for forecasting and classification
- Parameters – learning rate, regularization, momentum
- Building neural networks in Python
- Evaluating the performance of neural networks 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 Networks
- Recursive Neural Networks
- Recurrent Neural Networks
- Overview of libraries and interfaces available in Python
- Caffe
- Theano
- TensorFlow
- Keras
- Mxnet
- Selecting the appropriate library for a given 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 the architecture
- Tuning the network – initialization, activation functions, loss functions, and optimization methods
- Avoiding overfitting – detecting overfitting issues in deep networks and applying regularization
- Evaluating deep networks
- Case studies in Python
- Image recognition – CNN
- Detecting anomalies using Autoencoders
- Forecasting time series with RNN
- Dimensionality reduction with Autoencoders
- Classification using RBM
Requirements
Knowledge or appreciation of machine learning, system architecture, and programming languages is desirable.
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
