Abstract: . . .  psycholinguistics Page 1 An introduction to computational psycholinguistics : Modeling human sentence processing Shravan Vasishth University of Potsdam, Germany http://www.ling.uni-potsdam.de/~vasishth vasishth@acm.org September 2005, Bochum Neural structure 1 Page 2 A model of the neuron 2 Activation functions for translating net input to activation 3 Page 3 A model of layered neural connections 4 Five . . .
. . .  psycholinguistics Page 1 An introduction to computational psycholinguistics : Modeling human sentence processing Shravan Vasishth University of Potsdam, Germany http://www.ling.uni-potsdam.de/~vasishth vasishth@acm.org September 2005, Bochum Neural structure 1 Page 2 A model of the neuron 2 Activation functions for translating net input to activation 3 Page 3 A model of layered neural connections 4 Five assumptions • . . .
. . .  whether SRNs could encode the claim that a composite capacity score of spatial, numerical, and verbal tasks can be reflected in the network’s skill level. • Distance and interference effects: How do SRNs deal with those? (Konieczny, 2000), (Lewis & Vasishth, 2005), (Suckow et al., 2005), (Van Dyke & Lewis, 2003), (Vasishth & Lewis, 2005). . . 50 Closing remarks • Connectionist modeling has many important insights for us, about the role of experience, subtle emergent properties of architectures. • But as you may have found while doing the demos, it’s sometimes nontrivial to replicate a result. This brings up the question of free parameters in the model. What are the free parameters in connectionist models? We know that architectures like ACT-R have . . .
. . .  Results for the RC experiment • Averaging over RC type, lower error for high-span subjects at main verb. • Averaging over epochs, lower error at the main verb in subject RCs. • Epoch × RC type: in SRCs no effect of epoch, but in ORCs 3-epoch runs has lower error at the main verb. 48 Conclusions • “First, capacity is not some primitive, independent property of networks or humans in our account but is instead strictly emergent from other architectural and experiential factors.” • “Second, capacity is not independent of knowledge, so that one cannot manipulate factors underlying the capacity of a network (e.g. hidden unit layer size, activation function, weight decay, connectivity pattern, training) without also affecting the knowledge embedded . . .
--3000,4,375,2621,23497