convolutional neural network
A neural network loosely modeled on the visual system in which each neuron responds to a small receptive field via a convolution operation, emergently developing feature detectors like edge detectors.
As defined in 68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense
Other definitions
A neural network architecture that exploits local spatial structure in data (like images) by using localized connections between neurons, enabling efficient pattern recognition in visual data
The AI Expert: "Super AI Will Be Unstoppable!" – What’s Coming NEXT | Stephen Wolfram
Where it comes up · 9
- Machine Learning in Investing1 claim
- Nat Friedman (Github CEO) — Reading ancient scrolls, open source, & AI1 claim
- Yann LeCun's $1B Bet Against LLMs [Part 1]1 claim
- 15 | David Poeppel on Thought, Language, and How to Understand the Brain1 claim
- 280 | François Chollet on Deep Learning and the Meaning of Intelligence1 claim
- 298 | Jeff Lichtman on the Wiring Diagram of the Brain1 claim
- 68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense1 claim
- The Mastermind Behind GPT-4 and the Future of AI | Ilya Sutskever1 claim
and 1 more
Most important claims · 9 of 9Search all claims for “convolutional neural network” →
- Modern convolutional neural networks are based on the original studies of Nobel laureates Hubel and Wiesel on how visual information of the world is broken down into very small features in the visual cortex and then reassembled to produce perception.298 | Jeff Lichtman on the Wiring Diagram of the Brain
- Convolutional neural networks are loosely modeled on the visual system, where each neuron has a small receptive field and performs a convolution; when trained on many images, the lowest layer spontaneously develops edge detectors just like the brain's visual neurons described by Hubel and Wiesel, without being explicitly programmed to do so.68 | Melanie Mitchell on Artificial Intelligence and the Challenge of Common Sense
- Hypothesis-free big-data and machine-learning approaches in neuroscience, while powerful for classification problems, are essentially the mother of all regressions and risk making the field theoretically myopic—yielding only one form of answer and blinding researchers to theoretical alternatives—and ultimately require reinventing hypothesis-driven 'normal science' to interpret the model's parameters; engineering is thereby superseding science.15 | David Poeppel on Thought, Language, and How to Understand the Brain
- LeCun pioneered convolutional neural networks in the 1980s during expert systems era, and 25 years later AlexNet's breakthrough architecture was uncannily similar to LeCun's 1990s convolutional nets, validating his early insights.Yann LeCun's $1B Bet Against LLMs [Part 1]
- Decision trees work well when data can be cleanly split at each branch, as with categorical demographic variables for voting prediction, but they perform poorly on data like email or images where no clean bisection exists and where convolutional networks combine neighboring inputs instead.Machine Learning in Investing
- Hubel and Wiesel won a Nobel Prize in the late 1990s for research on the visual cortex of cats, discovering that visual processing works by learning hierarchies of representation (edges, contours, abstract shapes), which later inspired the architecture of convolutional neural networks used in face detection and object detection.Architecting Agent Memory: Principles, Patterns, and Best Practices — Richmond Alake, MongoDB
- A convolutional neural network can detect the ink inside Herculaneum scrolls from X-ray scans even though the ink is barely more X-ray-absorbent than papyrus and humans cannot see it in any rendering, because the model picks up subtle high-resolution patterns in X-ray absorption.Nat Friedman (Github CEO) — Reading ancient scrolls, open source, & AI
- Jeff Hinton told the interviewer that Sutskever was the main impetus behind AlexNet, the convolutional neural network that dramatically outperformed previous approaches in 2012 and initiated the deep learning revolution.The Mastermind Behind GPT-4 and the Future of AI | Ilya Sutskever
- Machine learning did not begin its popularity with connectionist methods: after early neural networks came SVMs, then random forests (popular ~2000-2010), then gradient-boosted trees—none neural-net or curve-fitting based—before the deep learning rebirth around 2011-2012 with GPU-trained convolutional networks, culminating in the 2012 ImageNet breakthrough.280 | François Chollet on Deep Learning and the Meaning of Intelligence