Course Outline
Foundations of Deep Learning in Natural Language Processing
Distinguishing between various types of Deep Learning models
Comparing the use of pre-trained versus custom-trained models
Extracting semantic meaning from text using word embeddings and sentiment analysis
Understanding the mechanics of Unsupervised Deep Learning
Installation and configuration of Python Deep Learning libraries
Leveraging the Keras Deep Learning library over TensorFlow to enable caption generation in Python
Integrating Theano (numerical computation) and TensorFlow (general and linguistic processing) as extended Deep Learning frameworks for caption creation
Utilizing Keras atop TensorFlow or Theano for rapid prototyping in Deep Learning
Building a basic Deep Learning application in TensorFlow to add captions to image collections
Common issues and troubleshooting strategies
An overview of other specialized Deep Learning frameworks
Strategies for deploying Deep Learning applications
Optimizing Deep Learning performance using GPUs
Concluding insights and next steps
Requirements
- Familiarity with Python programming fundamentals.
- General knowledge of the Python ecosystem and its available libraries.
Target Audience
- Developers with an interest in linguistics and language structures.
- Professionals seeking to deepen their understanding of Natural Language Processing (NLP).
Testimonials (2)
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
Magdalena - Samsung Electronics Polska Sp. z o.o.
Course - Deep Learning with TensorFlow 2
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
