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.
Convolutional Neural Networks
Explore deep learning for computer vision, covering CNNs, object detection, and image segmentation. Learn about architectures, applications, and impacts in various fields.
How Convolution Works
Guided tour of 2D convolution for CNNs and image processing, covering element-wise operations, feature detection, kernels, and practical applications.
How Convolutional Neural Networks Work, in Depth
Comprehensive exploration of convolutional neural networks, covering their structure, operation, and training process, including key concepts like filtering, pooling, and backpropagation.
Recurrent Neural Networks and Long Short-Term Memory
Explore recurrent neural networks and LSTM, their applications in sequence prediction, and practical uses in machine learning and AI.
3D Deep Learning for Gaming with Srinath Sridhar and Stanford Artificial Intelligence
Explore 3D deep learning for gaming, covering human pose estimation, object reconstruction, and computer vision applications with Stanford AI expert Srinath Sridhar.
Semi-Supervised Learning with GANs in Keras
Explore semi-supervised learning with GANs in Keras, focusing on training discriminators as classifiers using limited labeled data for improved accuracy compared to traditional CNNs.
Semi-Supervised Learning with GANs
Explore semi-supervised learning with GANs, focusing on training discriminators as classifiers using limited labeled data for improved accuracy compared to traditional CNNs.
Single Image Super Resolution Using SRGAN
Explore single image super-resolution using SRGAN, covering key concepts, perceptual loss, content loss, and network architectures for enhanced image quality.
Unpaired Image to Image Translation Using CycleGAN - An Introduction
Introduction to CycleGAN for unpaired image-to-image translation, covering key concepts, architecture, and training process. Explores discriminator and generator components, focusing on PatchGAN and instance normalization.
Image to Image Translation Using Pix2Pix GAN
Learn image-to-image translation using Pix2Pix GAN, exploring key concepts, generator and discriminator architectures, and practical applications in satellite imagery and scientific image generation.
Meta-Learning - Why It’s Hard and What We Can Do - Ke Li
Explore meta-learning challenges and solutions with Ke Li, covering optimization, model selection, and program induction in this theoretical machine learning seminar.
Understanding Deep Neural Networks - From Generalization to Interpretability
Explore deep neural networks, focusing on generalization and interpretability. Delve into graph convolutional networks, spectral filtering, and transferability. Examine fundamental questions and relevance mapping in machine learning.
Nonlinear Independent Component Analysis - Aapo Hyvärinen
Explore nonlinear independent component analysis, its applications in AI and unsupervised learning, and recent advancements in deep latent variable models with Aapo Hyvärinen.
The Challenges of Model-Based Reinforcement Learning and How to Overcome Them - Csaba Szepesvári
Explore challenges in model-based reinforcement learning, including modeling errors and efficient planning, and discover strategies to overcome them in complex environments.
Neural SDEs - Deep Generative Models in the Diffusion Limit - Maxim Raginsky
Explore deep generative models through stochastic control, diffusion limits, and neural nets. Learn about efficient sampling, expressiveness quantification, and unbiased simulation techniques.
On the Connection Between Neural Networks and Kernels: A Modern Perspective - Simon Du
Explore connections between neural networks and kernels, focusing on over-parameterization, generalization, and neural tangent kernels. Insights on training dynamics and applications to various learning tasks.
Fixing GAN Optimization Through Competitive Gradient Descent - Anima Anandkumar
Explore competitive gradient descent for optimizing GANs, covering strategic equilibria, applications in ML, and numerical results. Gain insights into modeling competing agents and solving GANs.
Emergent Linguistic Structure in Deep Contextual Neural Word Representations - Chris Manning
Explore emergent linguistic structures in deep neural word representations with Stanford's Chris Manning, examining language models, attention mechanisms, and vector space analysis.
The Epistemology of Deep Learning - Yann LeCun
Explore deep learning's scientific foundations with Yann LeCun, examining its biological inspirations, historical development, and theoretical underpinnings in pattern recognition and neural networks.
A Practical Guide to Deep Learning - Richard Zemel
Explore deep learning fundamentals, from perceptrons to neural networks, with practical insights on object recognition, vision, and advanced techniques like regularization.