Human-level concept learning through probabilistic program induction
Explore this paper's citation graph
Summary
A computational model is described that learns in a similar fashion and does so better than current deep learning algorithms and can generate new letters of the alphabet that look “right” as judged by Turing-like tests of the model's output in comparison to what real humans produce.
- Type
- article
- Published
- 2015-12-11
- Cited by
- 3,352
- References
- 98
- OpenAlex
- https://openalex.org/W2194321275
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:11790493
Keywords
Computer science, Alphabet, Artificial intelligence, Probabilistic logic, Turing
References
- Learning a theory of causality.
- How Children Learn to Write Words
- Probabilistic machine learning and artificial intelligence
- Parts of recognition
- Reading in the brain
- Perceptual organization in vision : behavioral and neural perspectives
- Language and Perception
- Structured imagination: The role of category structure in exemplar generation.
- The psychology of computer vision
- The Structure of Perceptual Categories
- The importance of shape in early lexical learning
- A probabilistic account of exemplar and category generation.
- Word learning as Bayesian inference.
- A Large-Scale Model of the Functioning Brain
- “The grammar of action”: Sequence and syntax in children's copying☆
- Referential communication and category acquisition.
- Stroke segmentation by bernstein-bezier curve fitting
- Ad hoc categories
- Using Generative Models for Handwritten Digit Recognition
- A Bayesian Analysis of Some Nonparametric Problems
Cited by
- Dynamic Signature Verification System Based on One Real Signature
- Parallel Distributed Processing Theory in the Age of Deep Networks.
- A machine learning model with human cognitive biases capable of learning from small and biased datasets
- Optimality and heuristics in perceptual neuroscience
- Cognitive Science: An Introduction to the Science of the Mind
- Towards more human-like concept learning in machines : compositionality, causality, and learning-to-learn
- Big Learning with Bayesian Methods
- Transitive Transfer Learning
- The Direction of Causation
- Deep Learning in Finance
- Understanding Visual Concepts with Continuation Learning
- Toward the neural implementation of structure learning.
- One-Shot Generalization in Deep Generative Models
- Classical Statistics and Statistical Learning in Imaging Neuroscience
- Interactive machine learning for health informatics: when do we need the human-in-the-loop?
- A Novel Biologically Mechanism-Based Visual Cognition Model-Automatic Extraction of Semantics, Formation of Integrated Concepts and Re-selection Features for Ambiguity
- Research Update: The materials genome initiative: Data sharing and the impact of collaborative ab initio databases
- Expanding perspectives on cognition in humans, animals, and machines
- Neural Networks for Modeling and Control of Particle Accelerators
- Progress in Fully Automated Abdominal CT Interpretation