Alexander Amini Courses

Deep Generative Modeling

1 review

Explore deep generative modeling, including autoencoders, variational autoencoders, and GANs. Learn about latent variable models, reparameterization tricks, and recent advances in generative AI techniques.

• YouTube
• 1 hour 2 minutes
• On-Demand
• Free Video

Visualization for Machine Learning - Google Brain

Explore data visualization techniques for machine learning, including high-dimensional data, multilingual systems, and language models, with insights on biases and user intent.

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

MIT: Image Domain Transfer - NVIDIA Guest Lecture

Explore image domain transfer techniques, from artistic style transfer to multimodal translations, with applications in photo smoothing, seasonal transformations, and game engines.

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

Biologically Inspired Neural Networks

Explore biologically plausible learning algorithms for neural networks, inspired by brain function. Discover synaptic plasticity rules and their application in deep learning architectures.

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

MIT 6.S191 - Deep Learning Limitations and New Frontiers

Explore deep learning limitations, adversarial attacks, uncertainty quantification, and AutoML in this lecture. Gain insights into neural network challenges and emerging frontiers in AI research.

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

MIT: Deep Reinforcement Learning

Explore deep reinforcement learning concepts, algorithms, and applications, including Q-learning, policy gradients, and breakthroughs like AlphaGo and AlphaZero in game AI.

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

Deep Generative Modeling

Explore deep generative modeling, including autoencoders, VAEs, and GANs. Learn about latent variables, representation learning, and applications in image generation and domain transformation.

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

Convolutional Neural Networks

Explore convolutional neural networks for computer vision tasks, covering feature extraction, convolution operations, and applications in classification, segmentation, and image captioning.

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

MIT: Recurrent Neural Networks

Explore deep sequence modeling with recurrent neural networks, including LSTMs and attention mechanisms. Learn to tackle challenges like vanishing gradients and long-term dependencies in sequence tasks.

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

MIT: Introduction to Deep Learning

Foundations of deep learning: perceptrons, neural networks, loss functions, backpropagation, optimization techniques, and strategies to prevent overfitting in neural network training.

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

Learning Steering for Parallel Autonomy

Explores end-to-end learning for parallel autonomy in self-driving cars, focusing on handling ambiguity, uncertainty estimation, and decision-making capabilities beyond reactionary control.

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

Computer Vision Meets Social Networks

Explore the intersection of computer vision and social networks, covering low-light enhancement, pose estimation, video attractiveness, classification, captioning, and natural language localization.

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

Sequence Modeling with Neural Networks

Explore sequence modeling with neural networks, focusing on RNNs, their challenges, and solutions like gated cells. Learn applications in music generation and machine translation.

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

Beyond Deep Learning - Learning+Reasoning

Explore advanced AI concepts beyond deep learning, focusing on integrating reasoning with learning for more robust and interpretable systems in this IBM Research lecture.

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

Deep Learning Limitations and New Frontiers

Explore deep learning limitations, new frontiers, and advancements in AI, including uncertainty estimation, adversarial attacks, and meta-learning, with insights on future developments and applications.

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