{"pk":26972,"title":"Converting Cascade-Correlation Neural Nets into Probabilistic Generative Models","subtitle":null,"abstract":"Humans are not only adept in recognizing what class an in-put instance belongs to (i.e., classification task), but perhapsmore remarkably, they can imagine (i.e., generate) plausibleinstances of a desired class with ease, when prompted. Inspiredby this, we propose a framework which allows transformingCascade-Correlation Neural Networks (CCNNs) into proba-bilistic generative models, thereby enabling CCNNs to gen-erate samples from a category of interest. CCNNs are a well-known class of deterministic, discriminative NNs, which au-tonomously construct their topology, and have been successfulin accounting for a variety of psychological phenomena. Ourproposed framework is based on a Markov Chain Monte Carlo(MCMC) method, called the Metropolis-adjusted Langevin al-gorithm, which capitalizes on the gradient information of thetarget distribution to direct its explorations towards regionsof high probability, thereby achieving good mixing proper-ties. Through extensive simulations, we demonstrate the effi-cacy of our proposed framework. Importantly, our frameworkbridges computational, algorithmic, and implementational lev-els of analysis.","language":"eng","license":{"name":"","short_name":"","text":null,"url":""},"keywords":[{"word":"Deterministic Discriminative Neural Networks;Probabilistic Generative Models; Markov Chain Monte Carlo"}],"section":"Talks: Papers","is_remote":true,"remote_url":"https://escholarship.org/uc/item/04h8p11w","frozenauthors":[{"first_name":"Ardavan","middle_name":"S.","last_name":"Nobandegani","name_suffix":"","institution":"McGill University","department":""},{"first_name":"Thomas","middle_name":"R.","last_name":"Shultz","name_suffix":"","institution":"McGill University","department":""}],"date_submitted":null,"date_accepted":null,"date_published":"2017-01-01T18:00:00Z","render_galley":null,"galleys":[{"label":"PDF","type":"pdf","path":"https://journalpub.escholarship.org/cognitivesciencesociety/article/26972/galley/16608/download/"}]}