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
Deep Learning Compared to Machine Learning and Other Approaches
- Appropriate scenarios for Deep Learning
- Constraints and limitations of Deep Learning
- Evaluating accuracy and costs across various methods
Overview of Techniques
- Network architectures and layers
- Forward and Backward propagation: key computations for layered compositional models
- Loss functions: defining the learning objective
- Solvers: managing model optimization
- Layer Registry: the fundamental building block for modeling and computation
- Convolutional operations
Techniques and Architectures
- Backpropagation and modular model design
- Log-sum module
- RBF Networks
- MAP and MLE loss functions
- Parameter Space Transformations
- Convolutional modules
- Gradient-based learning
- Energy functions for inference
- Learning objectives
- PCA and NLL
- Latent Variable Models
- Probabilistic LVM
- Loss functions
- Object detection using Fast R-CNN
- Sequence processing with LSTMs and Vision-Language integration with LRCN
- Pixel-wise prediction using Fully Convolutional Networks (FCNs)
- Framework architecture and future developments
Software Tools
- Caffe
- TensorFlow
- R
- Matlab
- Other tools
Requirements
A foundational understanding of any programming language is necessary. While not mandatory, prior knowledge of Machine Learning is advantageous.
21 Hours
Testimonials (3)
I really liked the end where we took the time to play around with CHAT GPT. The room was not set up the best for this- instead of one large table a couple of small ones so we could get into small groups and brainstorm would have helped
Nola - Laramie County Community College
Course - Artificial Intelligence (AI) Overview
Working from first principles in a focused way, and moving to applying case studies within the same day
Maggie Webb - Department of Jobs, Regions, and Precincts
Course - Artificial Neural Networks, Machine Learning, Deep Thinking
It felt like we were going through directly relevant information at a good pace (i.e. no filler material)
