Training Strategies in an SRNN

Leibovitz, D. P. (2006) Training Strategies in an SRNN. Working Paper, pp. 1-5. Carleton University. [doi: 10.13140/RG.2.1.2035.2483] (pdf)

Leibovitz (2006) Training Strategies in an SRNNAbstract: The effects of various training strategies are investigated on a Simple Recurrent Neural Network (SRNN) that learned to emulate an 8-Digit up/down/resettable counter.


Ottawa-Gatineau Region High-Tech Companies, Agencies, Job Boards, Etc.

Leibovitz, D. P. (2003-6) OttHtJobs: Ottawa-Gatineau Region High-Tech Companies, Agencies, Job Boards, Etc. Retrieved September 4, 2015 from [doi: 10.13140/RG.2.1.4714.9282]

Abstract: Here are 2000+ links to career pages of every high-tech related company, agency or job board in the Ottawa-Gatineau Region.

Every day, all these sites are scanned, and new job opportunities found are emailed to subscribers.

This job site was founded in 2003 and became inactive in 2006 at which time it had over 4000 subscribers.


Distinctive Serial Recall Effects

Leibovitz, D. P., Nath, U., Sedghi, R., Verger, D. (2006) Distinctive Serial Recall Effects. Poster presented at the Cognitive Science Spring Conference of Carleton University, pp. 1-18, Ottawa, Ontario, Canada. [doi: 10.13140/RG.2.1.2012.5926]

Leibovitz, Nath, Sedghi & Verger (2006) Distinctive Serial Recall EffectsAbstract: The study of word-length effect concentrated mostly on the accuracy of recalling short and long words in both pure and mixed lists. Previous studies showed that pure long lists were much poorly remembered. Hulme et al. (2004) found that word-length effect could be abolished in mixed lists when the short and long words are alternated. We investigated distinctiveness and found it to be a salient cue for improved correct recall when the list of words has a single distinctive transition. Lists contained three short words following by three long words and vice versa. Surprisingly, in the short-long condition, there was also an improvement in position 3 recall. One of the possible explanations could be the strategic shift of working memory resource.