Networks Are Like Onions - Practical Deep Learning with TensorFlow

Overview

Hands-on tutorial on building neural networks with TensorFlow for computer vision and NLP tasks. Learn key deep learning concepts and gain practical experience in shaping network architectures.

Syllabus

• Introduction to Deep Learning and TensorFlow
Overview of deep learning and neural networks
Introduction to TensorFlow and its ecosystem
• Setting Up Your Environment
Installing TensorFlow and essential libraries
Overview of Jupyter notebooks and Google Colab
• Fundamentals of Neural Networks
Layers, nodes, and activation functions
Forward and backward propagation
Loss functions and optimization
• Building and Training Neural Networks with TensorFlow
Creating and compiling models
Training, evaluating, and saving models
• Practical Computer Vision with TensorFlow
Image data preprocessing and augmentation
Implementing Convolutional Neural Networks (CNNs)
Transfer learning with pre-trained models
Hands-on project: Image classification
• Natural Language Processing with TensorFlow
Text data preprocessing and tokenization
Implementing Recurrent Neural Networks (RNNs) and LSTMs
Using Transformers for NLP tasks
Hands-on project: Text classification and sentiment analysis
• Fine-Tuning Network Architectures
Hyperparameter tuning and model optimization
Techniques for reducing overfitting: regularization and dropout
• Deploying and Monitoring Models
Exporting and deploying models with TensorFlow Serving
Basics of model performance monitoring
• Ethical Considerations in AI and Deep Learning
Bias in AI systems
Best practices for ethical AI development
• Final Project
Building a custom deep learning application
Presentations and peer review
• Course Conclusion and Next Steps
Recap of key learnings
Resources for continued learning in deep learning and TensorFlow

Subjects

Conference Talks