
Hands-on exploration of Diffusion Models using Google Colab, covering probabilistic implementations and prebuilt models. Includes code examples and practical demonstrations of the denoising process.

Explore Variational AutoEncoders and Vector Quantized VAE, focusing on codebook explanations. Learn how these advanced techniques improve upon traditional autoencoders for better image generation and representation.

Explore AutoEncoders, latent space, and reconstruction error in VQGAN. Learn key concepts and their applications in AI, with practical examples and in-depth explanations.

Learn to create NeRF scenes from videos or images using NVIDIA Instant-ngp. This hands-on tutorial covers environment setup, data preparation, and various NeRF visualization techniques on Ubuntu 22.04.

Explore ruDALL-E, an open-source text-to-image model based on DALL-E. Learn about its architecture, models, and try it out in Google Colab for generating images from text descriptions.

Learn to create neural networks in PyTorch: design layers, implement forward functions, and adapt models for various data types. Hands-on examples cover basic to complex architectures for structured and unstructured data.

Learn Graph Neural Networks implementation in Python, covering graph representations, node embeddings, message passing, and practical applications using NetworkX and PyG libraries.

Comprehensive tutorial on MNIST problem and CNN solution using CNN Explainer. Covers dataset preparation, model architecture, training, and evaluation. Ideal for beginners in deep learning and neural networks.

Learn to build and visualize Perceptron and Feed Forward networks in Python using Keras and TensorFlow. Ideal for beginners, this hands-on tutorial covers network creation, visualization, and fundamental deep learning concepts.

Create and visualize your first neural network in Python using Keras and TensorFlow. Learn step-by-step, from basic concepts to building a sequential model, with helpful visualizations and a pre-trained network example.

Learn to visualize and improve deep learning neural networks, making them easier to understand and explain through code transformation and network visualization techniques.

Watch a puzzle machine tackle the world's hardest jigsaw—an all-white puzzle. Explore image processing, mathematical algorithms, and innovative engineering solutions in this challenging project.

Learn to create realistic 3D lighting effects in Photoshop, adding depth and texture to flat images. Master advanced techniques using lighting effects and texture channels for stunning visual results.

Explore the LLM tech stack, covering API-accessible and open-source models. Learn about ChatGLM-6B and gain insights into self-hosting options for large language models.

Explore social biases in text representations and their mitigation with NLP expert Danushka Bollegala. Learn about gender bias, word embeddings, masked language models, and multi-lingual bias evaluation in AI systems.

Explore new HDR features in Photoshop 2023's Camera Raw, including merging, display options, visualization, and tone mapping. Learn to create, enhance, and save true HDR images for stunning results.

Learn object detection with OpenCV for augmented reality applications. Recognize objects as triggers for AR functions, enhancing your robotics and mechatronics skills.

Learn to build a neural network for classification using PyTorch, covering data preparation, network structure, and implementation. Gain hands-on experience in deep learning fundamentals.

Explore recurrent neural networks, transformers, and attention mechanisms in deep learning. Learn design principles, applications, and advanced concepts like LSTM and backpropagation through time.

Learn to build a voice assistant using OpenAI Embeddings, ChatGPT, Whisper, and Eleven Labs APIs. Combine AI technologies for realistic voice responses and create a custom Q&A system with a Gradio UI.

Learn to create custom AI image models using Dreambooth and LoRA techniques. Explore image processing, checkpoint creation, and concept settings for tailored results in Stable Diffusion.