A Cognitive Model for Generalization during Sequential Learning

Table 4

Mean and standard error of RMS difference in the hidden layer activation for the common subtask between Base Task and the interfering task. The first row gives the RMS value for a BP network, the second row for a Leabra network with contextual cues of strength 1.0, the third row for a Leabra network with contextual cues of strength 0.35, and the fourth row for a Leabra network trained in an interleaved manner for the two tasks.

Network	5 Patterns Same	10 Patterns Same
BP	0.324 (±0.0080)	0.381 (±0.0067)
Context = 1.0	0.299 (±0.0044)	0.329 (±0.0060)
Context = 0.35	0.159 (±0.0060)	0.147 (±0.0052)
Interleaved	0.156 (±0.0053)	0.156 (±0.0083)