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)
- Why neural networks and deep learning are necessary
- Selecting appropriate networks for various problems and data types
- Training and validating neural networks
- Comparing logistic regression to neural networks
- Neural Networks
- Biological inspiration behind neural networks
- Core components: Neurons, Perceptrons, and MLP (Multilayer Perceptron)
- MLP learning through the backpropagation algorithm
- Activation functions: Linear, Sigmoid, Tanh, and Softmax
- Loss functions suitable for forecasting and classification
- Key parameters: learning rate, regularization, and momentum
- Constructing neural networks in Python
- Evaluating neural network performance in Python
- Basics of Deep Networks
- Defining deep learning
- Deep network architecture: parameters, layers, activation functions, loss functions, and solvers
- Restricted Boltzmann Machines (RBMs)
- Autoencoders
- Deep Network Architectures
- Deep Belief Networks (DBN) – architecture and applications
- Autoencoders
- Restricted Boltzmann Machines
- Convolutional Neural Networks (CNN)
- Recursive Neural Networks
- Recurrent Neural Networks (RNN)
- Overview of Python Libraries and Interfaces
- Caffe
- Theano
- TensorFlow
- Keras
- MxNet
- Strategies for choosing the appropriate library for a specific problem
- Building Deep Networks in Python
- Selecting the right 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, and optimization methods
- Preventing overfitting: identifying overfitting issues and applying regularization
- Evaluating deep networks
- Python Case Studies
- Image recognition using CNN
- Anomaly detection with Autoencoders
- Time series forecasting with RNN
- Dimensionality reduction using Autoencoders
- Classification using RBM
Requirements
Desirable: Familiarity and appreciation for machine learning, system architecture, and programming languages.
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
