Human-level concept learning through probabilistic program induction
Brenden M. Lake, Ruslan Salakhutdinov, Joshua B. Tenenbaum · Science · 2015
People learning new concepts can often generalize successfully from just a single example, yet machine learning algorithms typically require tens or hundreds of examples to perform with similar accuracy. People can also use learned concepts in richer ways than conventional algorithms-for action, imagination, and explanation. We present a computational model that captures these human learning abilities for a large class of simple visual concepts: handwritten characters from the world's alphabets. The model represents concepts as simple programs that best explain observed examples under a Bayesian criterion. On a challenging one-shot classification task, the model achieves human-level performance while outperforming recent deep learning approaches. We also present several "visual Turing tests" probing the model's creative generalization abilities, which in many cases are indistinguishable from human behavior.
Cited by 2,809 works. doi:10.1126/science.aab3050
Authors
References
- Gradient-based learning applied to document recognition
- Deep learning
- Backpropagation Applied to Handwritten Zip Code Recognition
- Dropout: a simple way to prevent neural networks from overfitting
- Caffe
- Object Detection with Discriminatively Trained Part-Based Models
- Human-level control through deep reinforcement learning
- A Theory of the Learnable
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups
- A theory of the learnable