Launchpad Courses

Multi-Scale Multi-Band DenseNets for Audio Source Separation

Explore multi-scale multi-band DenseNets for audio source separation, featuring innovative architecture with up-sampling, block skip connection, and band-dedicated dense blocks to improve performance and efficiency.

• YouTube
• 24 minutes
• On-Demand
• Free Video

Making a 2D GAN 3D Aware

Explore 3D-aware image generation by modifying StyleGANv2 with multiplane alpha maps and pose-conditioned discrimination, achieving high-quality, view-consistent results across diverse datasets.

• YouTube
• 22 minutes
• On-Demand
• Free Video

UniFormer

Explore video understanding with UniFormer, a novel approach addressing inefficiencies in video transformers for improved performance and pose estimation.

• YouTube
• 34 minutes
• On-Demand
• Free Video

Towards Real World Blind Face Restoration with Generative Facial Prior

Explore generative facial priors for real-world blind face restoration, including GFP-GAN, degradation removal, and channel-split spatial feature transform techniques.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Not Another Transformer, NNFormer Explained!

Explore nnFormer, a novel AI model architecture, its envelope, mass data handling, and experimental results in this comprehensive overview.

• YouTube
• 27 minutes
• On-Demand
• Free Video

A Transformer-Based Framework for Multivariate Time Series Representation Learning

Explore a Transformer-based framework for multivariate time series analysis, covering challenges, model architecture, pre-training, fine-tuning, and applications in classification and forecasting.

• YouTube
• 21 minutes
• On-Demand
• Free Video

DF-GAN: Deep Fusion Generative Adversarial Networks for Text-to-Image Synthesis

Learn about DF-GAN, a deep fusion architecture for text-to-image synthesis. Explore its simplified backbone, gradient penalty, and deep fusion block, with quantitative and qualitative results.

• YouTube
• 38 minutes
• On-Demand
• Free Video

Deep Bayesian Bandits - Exploring in Online Personalized Recommendations

Explore online personalized recommendations using Deep Bayesian Bandits. Learn about UCB, Thompson Sampling, and innovative approaches like bootstrapping and dropout methods for effective exploration strategies.

• YouTube
• 29 minutes
• On-Demand
• Free Video

A Lip Sync Expert Is All You Need for Speech to Lip Generation in the Wild

Learn to generate realistic lip movements from speech using advanced AI techniques, exploring models, evaluation methods, and real-world applications in this cutting-edge field.

• YouTube
• 40 minutes
• On-Demand
• Free Video

Big Self-Supervised Models are Strong Semi-Supervised Learners

Explore cutting-edge semi-supervised learning techniques using large self-supervised models, examining their potential and impact on machine learning research and applications.

• YouTube
• 23 minutes
• On-Demand
• Free Video

Reinforcement Learning Based Speech Enhancement for Robust Speech Recognition

Explore innovative techniques for improving speech recognition using reinforcement learning-based speech enhancement, covering key concepts and potential future advancements.

• YouTube
• 31 minutes
• On-Demand
• Free Video

Reinforced Active Learning for Image Segmentation

Explore advanced techniques for image segmentation using reinforced active learning, covering challenges, algorithms, and experimental results.

• YouTube
• 24 minutes
• On-Demand
• Free Video

CNN Explainer - Learning Convolutional Neural Networks with Interactive Visualization

Interactive visualization tool for understanding convolutional neural networks, covering layers, filters, padding, activation, and pooling. Enhances learning through hands-on exploration.

• YouTube
• 25 minutes
• On-Demand
• Free Video

Self-Training With Noisy Student Improves ImageNet Classification

Explore advanced image classification techniques using self-training and noisy student methods, improving accuracy and robustness in deep learning models.

• YouTube
• 22 minutes
• On-Demand
• Free Video

Towards Deep Learning Models Resistant to Adversarial Attacks

Explore deep learning model vulnerabilities and defense strategies against adversarial attacks, examining research findings and experimental results.

• YouTube
• 23 minutes
• On-Demand
• Free Video