Shedding weights: More with less

—Traditional connectionist classification models place an emphasis on learned synaptic weights. Based on neurobiological evidence, a new approach is developed and experimentally shown to be more robust for disambiguating novel combinations of stimuli. It requires less training, variables and avoids many training related questions. Instead of determining all connection weights a-priori based on the training set, only positive binary associations are encoded (i.e. X has Y). Negative associations (i.e. X does not have Z) are not encoded, but inferred during the test phase through feedback connections. This allows the network to function outside its training distribution. For example, the network is able to recognize multiple stimuli even if it is only trained on single stimuli. We compare the accuracy and generalization of this network with traditional weight learning networks.

• Type: Conference
• Year: 2008
• Where: IJCNN
• Authors: Tsvi Achler, Cyrus Omar, Eyal Amir
• Keywords: Artificial Intelligence, IJCNN 2008, Positive Binary Associations, Training Related Questions, —Traditional Connectionist Classification