Tsvi Achler
Cognitive Computing
IBM Research, Almaden
Email: achler@gmail.com
Synthetic Cognition Group
Los Alamos National Labs
University of Illinois at Urbana Champaign
Thomas M. Seibel Center for Computer Science
RESEARCH INTERESTS:
Complex recognition abilities are inherent in even the simplest of organisms, yet is one of the most difficult problems in Computer Science. The responsible neural organization is yet unappreciated. Models based on biological insight can help both understanding of the brain and furthering Computer Science. Thus, I pursue a multidisciplinary approach to recognition-classification with a biological background (Neuroscience, Cognitive Psychology) as a guide and Computer Science as test bed.
One insight involves regulatory feedback connections (where cells feed back to their own inputs). This can be found ubiquitously in the brain including the well-studied olfactory bulb (which has at least two layers of feedback). However, most conventional artificial neural network theories do not incorporate feedback during their 'recognition phase'.
My models focus on regulatory feedback and less on connection strengths. Instead, top-down feedback continuously modifies input activation. The modified input activity is re-distributed to the network and receives feedback on this re-distribution. This is repeated iteratively to determine stimuli relevance.
Because 'salience' and effective connection weights are modified during recognition, the network is more flexible, combinatorially plausible, and learning is simpler. It behaves more informatively in complex scenarios, for example, multiple stimuli present in a scene. It can be used to explain several cognitive phenomena associated with search difficulty, competition and human reaction times. These findings question the traditional approach and offer a more biologically plausible, flexible and a dynamic approach to recognition.
Note: Over the years I have explored several names for this configuration including: Input Shunt Networks, Recurrent Loop Networks, Recurrent Feedback Neural Networks, Input Feedback Networks, Regulatory Feedback Networks. However, they all represent the same 'Feedback Inhibition Networks' and 'Supervised Generative Models'.REPRESENTATIVE WORK:
Papers / Proceedings
Achler, T., Non-Oscillatory Dynamics to Disambiguate Pattern Mixtures, Chapter 4 in Relevance of the Time Domain to Neural Network Models Editors: Rao R, Cecchi G A, Springer 2011. PDF
Achler, T., Bettencourt, L., Evaluating the Contribution of Top-Down Feedback and Post-Learning Reconstruction, Biologically Inspired Cognitive Architectures AAAI Proceedings, 2011. PDF
Achler, T., Amir, E., A Genetic Classifier Account for the Regulation of Expression, Editorys: Chaovalitwongse, Pardalos, Xanthopoulos. Computational Neuroscience, Springer, 2010. PDF
Achler, T., Vural D., Amir, E., Counting Objects with Biologically Inspired Regulatory-Feedback Networks, Neural Networks IJCNN IEEE Proceedings, 2009. PDF
Achler, T., Using Non-Oscillatory Dynamics to Disambiguate Simultaneous Patterns, Neural Networks IJCNN IEEE Proceedings, 2009. PDF
Achler, T., Omar C., Amir, E., Shedding Weights: More With Less, Neural Networks IJCNN IEEE Proceedings, 2008. PDF
Achler, T., Amir, E., Input Feedback Networks: Classification and Inference Based on Network Structure, Artificial General Intelligence AAAI Proceedings V1: 15-26, 2008. PDF.
Achler, T., Amir, E., Neuroscience and AI Share the Same Elegant Mathematical Trap, Artificial General Intelligence Proceedings AAAI Proceedings V2, 2009. PDF.
Workshops / Tutorials
Tutorial - Plasticity Revisited: Motivating New Algorithms Based On Recent Neuroscience Research
Software