ConceptAI & ML
Convolutional neural networks
Neural network architectures specialized for processing grid-like data such as images using convolutions and subsampling.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Opens up
Concepts that name this one as a prerequisite.
Lecturers
9Each in their own terms, from the easiest level.
Yoshua Bengio
A special kind of neural network well suited for dealing with images by processing input in stages using convolution and non-linearity.Fei-Fei Li, Justin Johnson & Serena Yeung
A neural network architecture that uses convolutional layers to explicitly maintain spatial structure in data.Brian Yu
Neural networks that use convolution, usually for analyzing images.Josh McDermott
Machine systems consisting of cascades of simple operations like filtering, thresholding, pooling, and normalization arranged in multiple layers.Gilbert Strang
A neural network architecture that uses convolution layers to process image data efficiently by sharing weights along diagonals instead of using full weight matrices.Barbara Kwiecinska
Neural networks inspired by the animal visual cortex designed to automatically and adaptively learn spatial hierarchies of features via filter optimization.Melanie Mitchell
A deep neural network architecture where layers extract spatial features hierarchically from images to output concept probabilities.Elahe Kamel Targhi
Deep learning models known to understand patterns in data and correlate them to outputs.
Lectures that assume it
25The first 12 are shown.
- Building makemore Part 5: Hierarchical Dilated Causal Convolutions (WaveNet)
- Training Neural Networks II
- CNN Architectures
- Detection and Segmentation
- Adversarial Examples and Adversarial Training
- Recurrent Neural Networks
- Arch4Health: 4th Workshop on Architecture for Health
- Architectures: Graphs
- Exploration of fundamental concepts in deep reinforcement learning
- Learning Representations: A Challenge for Learning Theory, COLT 2013
- Deep Learning Software
- Generative Models
Connections
45The lectures that define it or assume it, and the concepts next to it.
Concepts10
Show 4 moreShow fewer
Lectures35
- Harvard CS50’s Artificial Intelligence with Python – Full University Course
- Convolutional Neural Networks
- Object Recognition (cont'd), Texture Perception
- ImageNet and Convolutional Neural Networks
- Turing Lecture: Deep Learning for AI and System-2 Reasoning
- Introduction to Convolutional Neural Networks for Visual Recognition
Show 29 moreShow fewer
- Conceptual Abstraction and Analogy in Natural and Artificial Intelligence
- Introduction to Deep Learning
- From Outcrop Observations to Dynamic Simulations: Generating Geologically Plausible Fracture Networks
- Current & Future Application of AI in Epilepsy by Dr. Barbara Kwiecinska, PGY4 Neurology Resident
- Building makemore Part 5: Hierarchical Dilated Causal Convolutions (WaveNet)
- Training Neural Networks II
- CNN Architectures
- Detection and Segmentation
- Adversarial Examples and Adversarial Training
- Recurrent Neural Networks
- Arch4Health: 4th Workshop on Architecture for Health
- Architectures: Graphs
- Exploration of fundamental concepts in deep reinforcement learning
- Learning Representations: A Challenge for Learning Theory, COLT 2013
- Deep Learning Software
- Generative Models
- Generative Models: Conditional Models
- Architectures: Grids
- Efficient Methods and Hardware for Deep Learning
- Generalization Theory
- Architectures: Transformers
- Representation Learning: Reconstruction-Based
- Transformers in Diffusion Models for Image Generation and Beyond
- Transformers in Vision: Tackling problems in Computer Vision
- Visualizing and Understanding
- Scalability in Autonomous Driving (CVPR 2020 Keynote)
- Scientific Machine Learning for Electromagnetic Field Computations
- Overview of Transformers (Stanford CS25: Transformers United V6)
- #HEMEPATH Spotlight on Innovation: Practical Advances in Rare and Orphan Hematologic Diseases