Deep Learning Developer: Foundations of Deep Learning
This three day workshop is designed to introduce participants to the skills needed to start their journey as a Deep Learning Developer. It goes through the overall concepts and techniques for building a variety of Deep Learning models for tabular data, image data, audio data and text data.
What You'll Learn
- ✓ Building Dense, CNN and RNNs Neural Networks in TensorFlow
- ✓ How to build models with the TensorFlow Sequential and Functional APIs
- ✓ The theory behind Convolutional and Recurrent Neural Networks
- ✓ How to use ImageNet models for Transfer Learning
- ✓ Building models with Embeddings for NLP
- ✓ Building models for Tabular Data using Pandas and TensorFlow
This three-day workshop is designed to introduce participants to the skills needed to start their journey as a Deep Learning Developer. It goes through the overall concepts and techniques for building a variety of Deep Learning models for tabular data, image data, audio data, and text data.
The 3 days are split based on the type of neural network architectures, their related tasks, and use cases.
Day 1: Fully Connected Networks and Tabular data
The first day covers both basics of Machine Learning and Deep Learning and prepares students to build basic fully connected networks, understand the mathematics behind these networks and how techniques like backpropagation, dense layers and cross entropy losses work.
These techniques will then be applied across multiple networks in TensorFlow for various prediction tasks before focusing on building models for Tabular data using these fully connected networks.
Day 2: Vision and Convolutional Neural Networks
The second day covers CNNs and their corresponding layers, components, and how to use them for a number of tasks. These include classification from scratch with CNNs, using pre-trained CNN ImageNet models for Transfer Learning classification, and treating audio as images for simple audio classification.
We also cover the basics of Object Detection, using a pre-trained TensorFlow Object Detection model.
Day 3: Text and Transformers
The third day covers both the theory and applications of transformers for tasks such as text classification and text generation. We also look at using frameworks that implement a pre-trained modern transformer such as BERT and explore Latent Language Models (LLMs) for various tasks including summarization, translation, and question-answering.
Each day will also have in-class challenges. These will sometimes involve fixing code with (deliberate) bugs in it, or creating a model from scratch given the data with some preprocessing code.
The In-class Challenges for the Foundations of Deep Learning are as follows:
- Day 1: MLP Model on Vectors
- Day 2: ImageNette (Reduced ImageNet Data) 3 channel CNN model from scratch
- Day 3: IMDB Movie Sentiment with BERT
At the end of the classroom training, participants will work on their models and projects. Additional learning materials and assessments will be available online, with one-on-one sessions for you to ask questions on your project. This is especially useful for understanding how to apply these skills for your unique applications.
Overall, the curriculum will cover many of the fundamentals needed in Deep Learning projects, as well as models such as Fully Connected Neural Networks, Convolutional Neural Networks, and Transformers. Real-world examples will be used to identify the best techniques to tackle various data science problems at hand.
In this course, participants will learn:
- The basic concepts of Neural Networks and an introduction to the mathematics of Deep Learning
- An introduction to the Keras API and how it works as a higher level of abstraction for TensorFlow, PyTorch & JAX
- To build and use Keras models with TensorFlow and PyTorch.
- To build various types of Deep Learning models
- To build models for Computer Vision tasks and challenges
- To build models for Natural Language Processing tasks
- Use a premade model for Object Detection
- Use BERT and other Transformers for Sentiment Analysis
- Applications of LLMs for a variety of tasks
Technologies we teach will include:
Earn a certificate upon completion
Time to Complete
Approx. 28 hours to complete
Why Study Artificial Inteligence?
1. Demand for AI/Dl jobs has never been at this all time high.
2. Developers need these skills
3. AI/DL Jobs pay more than standard developer jobs
Request More Info
Sign up to receive additional information about this course. Find out what other learners are doing with the skills they gamed, and evaluate if this course is the right fit for you.
Frequently Asked Questions
Do I have to log in at a set time? How does the 360-degree assessment work? At this point, you probably have a few questions, and we’ve got answers.