ConceptAI & ML
Inductive bias
The set of assumptions that a learning algorithm uses to predict outputs for inputs it has not encountered.
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.
Generalization5Machine learning models4Machine learning2Convolutional neural networks1Hypothesis space1Model architecture1Model generalization1Neural network architecture1
Opens up
Concepts that name this one as a prerequisite.
Lecturers
9Each in their own terms, from the easiest level.
Hyung Won Chung
Assumptions and structures built into a model to help it learn faster with less data, which can later act as a ceiling to scaling.Jason Wei & Hyung Won Chung
Additional structure or modeling assumptions imposed on a machine learning method to help it perform well under low-compute or low-data regimes.Sara Beery
Assumptions and structural priors built into a learning model about the kinds of functions it should expect to learn.Phillip Isola
Assumptions built into a learning algorithm that cause it to prefer certain solutions over others, enabling generalization.Stefano Ermon
The set of assumptions a model uses to predict outputs for inputs it has not encountered.Drew Jaegle
Assumptions built into a learning algorithm that help it generalize to unseen data.Tom Mitchell
The set of assumptions that a machine learning algorithm uses to predict outputs for unseen inputs.Lucas Beyer
Built-in assumptions like locality or translation equivariance that may limit models when scaling up data.
Lectures that assume it
2Connections
18The lectures that define it or assume it, and the concepts next to it.
Concepts7
- Generalization
- Machine learning
- Convolutional neural networks
- Hypothesis space
- Emergent behavior
- Explanation-based learning
Show 1 moreShow fewer
Lectures11
- Generative Modeling by Estimating Gradients of the Data Distribution
- DeepMind's Perceiver and Perceiver IO: New data family architecture
- Shaping the Future of AI from the History of Transformer Architectures
- Intuitions on Language Models and the History of Transformer Architectures
- Architectures: Grids
- Generalization Theory