Course: Deep Learning
Dive into the world of deep learning with our advanced training course designed for professionals seeking to elevate their expertise in artificial intelligence. This comprehensive program covers everything from the fundamental concepts of deep learning and neural networks to specialized techniques in computer vision. Participants will explore the structure and training processes of artificial neural networks (ANNs), learn to fine-tune models using cutting-edge methods, and gain hands-on experience with Keras to build powerful regression and convolutional neural network (CNN) models. Whether you're aiming to enhance your AI skill set or break into new technological frontiers, this course provides the tools and knowledge you need to develop state-of-the-art deep learning solutions.
Course Outcomes
Upon completion of this course, participants will:
- Grasp the core concepts of deep learning, and recognize the potential applications across various industries.
- Build and train neural networks, and effectively train and evaluate regression and classification models using Keras.
- Address Bias and Variance issues in neural networks using techniques like early stopping, regularization, and dropout, and fine-tune model hyperparameters with Keras Tuner.
- Understand the architecture of convolutional neural networks (CNNs), preprocess image data, and build, train, and evaluate CNN models with Keras for computer vision applications.
Who It's For
This course is ideal for:
- Data scientists and machine learning engineers
- AI enthusiasts and developers
- Researchers and academics
- Tech professionals transitioning to AI
- Graduate students in data science and AI
Prerequisites
- A fluent in Python, and its libraries NumPy, Pandas, and Matplotlib
- Prior experience with machine learning algorithms
- Completed "Machine Learning" course (Recommended)
Course Modules
1. Foundations of Deep Learning Models
- Understanding the intuition behind neural networks.
- Differentiating between machine learning and deep learning.
- Exploring key applications of deep learning.
2. Artificial Neural Networks (ANN)
- Examining the structure of neural networks.
- Delving into the ANN training process: forward and backward propagation, activation functions, epochs, and batches.
- Training and evaluating regression models using Keras.
- Training and evaluating classification models using Keras.
3. Tuning Artificial Neural Networks
- Addressing bias and variance in neural networks.
- Implementing techniques such as early stopping, regularization, and dropout.
- Fine-tuning hyperparameters using Keras Tuner.
4. Introduction to Computer Vision
- Understanding the architecture of convolutional neural networks (CNNs).
- Preprocessing image data for deep learning models.
- Training CNN models with Keras.
Execution approach:
Long run
30 hours
5 weeks
Run over short weekly sessions allowing participants to progressively build their skills and knowledge.
