Pages that link to "Item:Q1892207"

The following pages link to Characterizations of learnability for classes of \(\{0,\dots,n\}\)-valued functions (Q1892207):

Displaying 20 items.

• Learning with stochastic inputs and adversarial outputs (Q439998) (← links)
• Corrigendum to ``Shifting: One-inclusion mistake bounds and sample compression'' (Q972387) (← links)
• On the learnability of rich function classes (Q1305934) (← links)
• A result of Vapnik with applications (Q1314333) (← links)
• Sphere packing numbers for subsets of the Boolean \(n\)-cube with bounded Vapnik-Chervonenkis dimension (Q1345876) (← links)
• PAC-learning from general examples (Q1392015) (← links)
• Efficient algorithms for learning functions with bounded variation (Q1887165) (← links)
• On the complexity of function learning (Q1900975) (← links)
• Fat-shattering and the learnability of real-valued functions (Q1924381) (← links)
• PAC learnability under non-atomic measures: a problem by Vidyasagar (Q1939260) (← links)
• Primal and dual combinatorial dimensions (Q2112665) (← links)
• Shifting: one-inclusion mistake bounds and sample compression (Q2517823) (← links)
• On the complexity of computing and learning with multiplicative neural networks (Q2780854) (← links)
• Higher dimensional PAC learning (Q2799821) (← links)
• Sample Complexity of Classifiers Taking Values in ℝ^<i>Q</i>, Application to Multi-Class SVMs (Q3562430) (← links)
• Scale-sensitive dimensions, uniform convergence, and learnability (Q4377590) (← links)
• Inapproximability of Truthful Mechanisms via Generalizations of the Vapnik--Chervonenkis Dimension (Q4602545) (← links)
• Valid Generalisation from Approximate Interpolation (Q4715266) (← links)
• (Q5743481) (← links)
• Comments on: Support vector machines maximizing geometric margins for multi-class classification (Q5965492) (← links)