Learn how to apply transfer learning with pre-trained models like ResNet and BERT using TensorFlow, and fine-tune them for new tasks.
Learn about autoencoders, their architecture, and practical applications like anomaly detection, image denoising, and dimensionality reduction.
Learn about regularization techniques such as L1, L2 regularization, dropout, and early stopping to prevent overfitting in neural networks.
Learn the importance of hyperparameter tuning in machine learning, with an introduction to key hyperparameters and basic tuning methods like grid search and random search, along with practical tips to optimize model performance.
Learn how to train a Convolutional Neural Network (CNN) using TensorFlow on the MNIST dataset, a benchmark dataset for image classification.