(C) Copyright Elephant Scale August 14, 2022
Today, Deep Learning can accomplish results that are nothing short of miraculous. In this course, we assume that you do not want to re-invent wheels. Rather, you want to know what is available as low-hanging fruit. In other words, you are looking for magic but you don’t want to compete with teams who create this magic. You want to partner with them and achieve the same quality results but with a practical reasonable expense of time and resources.
- By the end of this course, students will know…
- How to understand the current state of the art in Deep Learning and AI
- How to put the claims of AI to the test
- How to utilize the existing results through transfer learning, pre-training, and fine-tuning.
- How to package your models for deployment.
- How to create machine learning pipelines and improve them in production.
- Developers, data scientists, team leads, project managers
- Two days
- General familiarity with machine learning
- Lectures and hands-on labs. (50% – 50%)
- Zero Install: There is no need to install software on students’ machines!
- A lab environment in the cloud will be provided for students.
Students will need the following
- A reasonably modern laptop with unrestricted connection to the Internet. Laptops with overly restrictive VPNs or firewalls may not work properly.
- A checklist to verify connectivity will be provided
- Chrome browser
Introduction to Deep Learning
- Understanding Deep Learning use cases
- Understanding AI / Machine Learning / Deep Learning
- Data and AI
- AI vocabulary
- Hardware and software ecosystem
- Understanding types of Machine Learning (Supervised / Unsupervised / Reinforcement)
- Introducing Convolutional Neural Networks (CNN)
- CNN architecture
- CNN concepts
- Lab: Image recognition using CNNs
Recurrent Neural Networks
- Introducing RNNs
- RNN architecture
- RNN concepts
- LSTM (Long Short Term Memory) networks
- LSTM architecture
- Lab: RNNs for text and sequence prediction
- Sequence to sequence
- Bias and limitations
- Putting it all together
Fine-tuning a pre-trained model
- Processing the data
- Fine-tuning a model with the Trainer API or Keras
- A full training
Sharing models and tokenizers
- The Hugging Face Hub
- Using pre-trained models
- Sharing pre-trained models
Main NLP tasks
- Token classification
- Fine-tuning a masked language model
- Training a causal language model from scratch
- Question answering
- Mastering NLP