The exponential learning equation as a function of successful trials results in sigmoid performance

By N. Leibowitz, Barak Baum, G. Enden, Amir Karniel. 2010

126 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Semi-analytical approximations to statistical moments of sigmoid and softmax mappings of normal variables (2017, background): “Applications of sigmoid mappings include, but are not limited to, the description of learning dynamics (see, e.g., Leibowitz et al., 2010) and psychometric functions (see, e.g., Wichmann and Hill, 2001), input/output relationships of artificial (see, e.g., Jain et al., 1996) and natural neurons…”
When Do You Need Billions of Words of Pretraining Data? (2020, methodology): “We use a four-parameter exponential learning curve used to capture diminishing improvement in performance as a function of the number of practice trials (Heathcote et al., 2000; Leibowitz et al., 2010):”
T-Drive: Enhancing Driving Directions with Taxi Drivers' Intelligence (2013, unknown): “P wip i k ; ð6Þ where the weight wi is the normalized familiarity of taxi driver i wi ¼ fðniÞPn i¼1 fðniÞ : ð7Þ”
Driving with knowledge from the physical world (2011, methodology): “The progress of a driver’s familiarity with a landmark edge is modeled using a Sigmoid learning curve [16] (as shown in Figure 3 B), defined as:”