The following pages link to Jonathan Baxter (Q1369060):
Displaying 9 items.
- A Bayesian/information theoretic model of learning to learn via multiple task sampling (Q1369061) (← links)
- Improved generalization through explicit optimization of margins (Q1568529) (← links)
- Learning to play chess using temporal differences (Q1584836) (← links)
- Estimation and approximation bounds for gradient-based reinforcement learning (Q1604222) (← links)
- (Q3093234) (← links)
- (Q4533362) (← links)
- (Q4533363) (← links)
- Emmerald: a fast matrix–matrix multiply using Intel's SSE instructions (Q4790974) (← links)
- (Q4852525) (← links)
