From biological models to the evolution of robot control systems

By John A. Bullinaria. 2003

25 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.

In Cell Biology

Citations in the corpus

Born to Learn: the Inspiration, Progress, and Future of Evolved Plastic Artificial Neural Networks (2017, background): “The seminal work in Bullinaria (2003, 2007a, 2009b) proposes the more general hypothesis that learning requires the evolution of long periods of parental protection and late onset of maturity.”
Understanding the Emergence of Modularity in Neural Systems (2007, methodology): “A potential difficulty, however, lies in the use of non-binary output targets for the SSE approach, which is now known to be a less than optimal way to proceed (Bullinaria, 2003a).”
The effect of learning on life history evolution (2007, unknown): “It has already been demonstrated elsewhere that evolving neural network learning rates that vary during the learning process does lead to improved learning performance, and that the evolved time dependencies are qualitatively similar to human like age dependencies [3, 5].”
Evolved Sensitive Periods in Learning (2013, background): “Bullinaria (2003) studied sensitive periods of learning, as part of a simulation of the human oculomotor system.”
The Importance of Neurophysiological Constraints for Modelling the Emergence of Modularity (background): “The incorporation of known neurophysiological constraints into the models is seen to be of crucial importance.”
Imitative and Direct Learning as Interacting Factors in Life History Evolution (2017, background): “Moreover, good adult behaviors will not necessarily be appropriate for newborn individuals, in the same way that learned adult neural connection strengths can be suboptimal for newborns [14], and having optimal innate behaviors will be difficult in spatially or temporally changing environments [23],”
Lifetime Learning as a Factor in Life History Evolution (2009, unknown): “It has certainly been demonstrated in previous computational studies that evolving neural network learning rates that vary during the learning process does lead to improved learning performance, and that the evolved time (t ) dependences are qualitatively similar to humanlike age dependences [7, 9, ”