Course Outline
- Backpropagation and modular models
- Log-sum module
- Radial Basis Function (RBF) networks
- Maximum A Posteriori (MAP) and Maximum Likelihood Estimation (MLE) loss
- Parameter space transforms
- Convolutional modules
- Gradient-based learning
- Energy methods for inference
- Learning objectives
- Principal Component Analysis (PCA) and negative log-likelihood (NLL)
- Latent variable models
- Probabilistic latent variable models
- Loss functions
- Handwriting recognition
Requirements
A solid foundation in fundamental machine learning principles. Proficiency in programming using any language (with Python or R being preferred).
Testimonials (7)
The structure from first principles, to case studies, to application.
Margaret Webb - Department of Jobs, Regions, and Precincts
Course - Introduction to Deep Learning
The deep knowledge of the trainer about the topic.
Sebastian Gorg
Course - Introduction to Deep Learning
I think that if training would be done in polish it would allow the trainer to share his knowledge more efficient.
Radek
Course - Introduction to Deep Learning
Exercises after each topic were really helpful, despite there were too complicated at the end. In general, the presented material was very interesting and involving! Exercises with image recognition were great.
Dolby Poland Sp. z o.o.
Course - Introduction to Deep Learning
Topic. Very interesting!.
Piotr
Course - Introduction to Deep Learning
Trainers theoretical knowledge and willingness to solve the problems with the participants after the training.
Grzegorz Mianowski
Course - Introduction to Deep Learning
The topic is very interesting.
