Generative Adversarial Networks (GANs)
Explore the theory and practice of Generative Adversarial Networks. Learn to build and train GANs for tasks like image generation, style transfer, and data augmentation.
120 courses
Learn the fundamentals of generative deep learning by writing, training, and evaluating adversarial models to generate realistic synthetic data.
Learn the core principles of generative AI by implementing, training, and evaluating your own GAN architectures using clean, modern PyTorch code.
Master the techniques to build, evaluate, and refine generative adversarial networks using modern metrics and advanced architectures like StyleGAN.
Master the mechanics of Generative Adversarial Networks to transform images, augment datasets, and understand synthetic data generation through written lessons.
Build generative models, apply neural style transfer, and design autoencoders using TensorFlow to create and transform image data from scratch.
Learn the fundamentals of how deepfakes are created, their real-world applications, and the critical ethical questions they raise.
Learn the core principles of deepfake creation and detection, exploring generative AI models and ethical implications through clear, step-by-step written guides.
Learn the fundamentals of generative deep learning to design, train, and evaluate your own Generative Adversarial Networks using modern AI frameworks.
Build and train generative models to produce detailed, high-quality images using Python and TensorFlow.
Learn how this essential technique improves training speed and stability in your deep learning models.
Learn to build and train your first generative adversarial networks using PyTorch to generate realistic synthetic data from scratch.
Build a strong foundation in generative AI, from VAEs and GANs to transformer architectures and modern retrieval-augmented generation techniques.
Understand the core concepts of Generative Adversarial Networks and apply PyTorch to develop models for generating realistic images.
Master the fundamentals of generative neural networks to reconstruct data, generate realistic images, and manipulate latent spaces through clear written explanations.
Master advanced feature extraction and pooling techniques in CNNs to optimize deep learning models for rare event prediction and classification tasks.
Master max pooling, global pooling, and advanced downsampling techniques in CNNs to improve feature extraction and model performance for rare event prediction.
Master the principles of compound scaling to build highly accurate, resource-efficient computer vision models for image classification.
Master the fundamentals of conditional GANs to generate targeted images by directing generative models with class labels using TensorFlow and Keras.
Learn how 3D objects are represented and projected in computer graphics to build a strong foundation for developing 3D-aware generative adversarial networks in PyTorch.
Understand how ResNet, Batch Normalization, and pre-activation stabilize training and enhance the performance of deep neural networks for computer vision.
Showing 20 of 120 courses