Version française en construction !

Articles and selected proceedings

(see CV for complete list)
  • Learning complex motor control with neurostimulation: a hierarchical andadaptive algorithm to optimally explore neural maps, SamuelLaferriere, Marco Bonizzato, Numa Dancause, and Guillaume Lajoie, (2019), preprint
  • Dimensionality compression and expansion in Deep Neural Networks, Stefano Recanatesi, Matthew Farrell, Madhu Advani, Timothy Moore, Guillaume Lajoie, Eric Shea-Brown, (2019) preprint
  • Dynamic compression and expansion in a classifying recurrent network, Matthew Farrell, Stefano Recanatesi, Guillaume Lajoie, and Eric Shea-Brown, (2019) preprint
  • Cortical network mechanisms of anodal and cathodal transcranial direct current stimulation in awake primates, Andrew R. Bogaard, Guillaume Lajoie, Hayley Boyd, Andrew Morse, Stavros Zanos, Eberhard E. Fetz, (2019), preprint
  • Signatures and mechanisms of low-dimensional neural predictive manifolds, Stefano Recanatesi, Matthew Farrell, Guillaume Lajoie, Sophie Deneve, Mattia Rigotti, Eric Shea-Brown, (2019) preprint
  • Non-normal Recurrent Neural Network (nnRNN): learning long time dependencies while improving expressivity with transient dynamics, Giancarlo Kerg, Kyle Goyette, Max- imilian Puelma Touzel, Gauthier Gidel, Eugene Vorontsov, Yoshua Bengio, and Guillaume Lajoie, (2019), 33rd Conference on Neural Information Processing Systems (NeurIPS) [Available here
  • ]
  • Rethinking Complexity in Deep Learning: A View from Function Space, A. Baratin, T. George, C. Laurent, V. Thomas, G. Lajoie, S. Lacoste-Julien, (2019), NeurIPS Workshop: Machine Learning with Guarantees
  • Recurrent neural networks learn robust representations by dynamically balancing compression and expansion, Matthew Farrell, Stefano Recanatesi, Guillaume Lajoie, Eric Shea-Brown, (2019), NeurIPS Workshop: Real Neurons & Hidden Units: Future directions at the intersection of neuroscience and artificial intelligence
  • Modelling Working Memory using Deep Recurrent Reinforcement Learning , Pravish Sainath, Pierre Bellec, Guillaume Lajoie, (2019), NeurIPS Workshop: Real Neurons & Hidden Units: Future directions at the intersection of neuroscience and artificial intelligence
  • Implicit Regularization in Deep Learning: A View from Function Space, A. Baratin, T. George, C. Laurent, V. Thomas, G. Lajoie, S. Lacoste-Julien, (2019), NeurIPS Workshop: Science meets Engineering of Deep Learning
  • Stochastic Gradient Descent drives dimensionality reduction in neural networks, M. Farrell, S. Recanatesi, M. Advani, T. Moore. G. Lajoie, E. Shea-Brown, Deep Math: Conference on the Mathematical Theory of Deep Neural Networks, New York, NY, USA, 10/2019
  • Learning to evoke complex motor outputs with spatiotemporal neurostimulation using a hierarchical and adaptive optimization algorithm., S. Laferriere, N. Dancause, M. Bonizzato, G. Lajoie, Conference on Cognitive Computational Neuroscience (CCN), Berlin, Germany, Sept. 2019
  • [Plenary talk]Learning to control muscles with a brain-computer interface: a hierarchical and adaptive algorithm to optimally explore neural maps., G. Lajoie, S. Laferriere, International Conference on Mathematical Neuroscience (ICMNS), Copenhagen, Denmark, June 2019
  • Rethinking Complexity in Deep Learning: A View from Function Space., A. Baratin, T. George, C. Laurent, V. Thomas, G. Lajoie, S. Lacoste-Julien, International Conference on Machine Learning (ICML) 2019 Workshop on Theoretical Physics for Deep Learning, Long Beach, USA, June 2019
  • Dimensionality expansion via chaotic dynamics facilitates classification in a trained network., M. Farrell, S.Recanatesi, T, Moore, G. Lajoie, E. Shea-Brown, Computational and Systems Neuroscience 18 (COSYNE), Lisbon, Portugal, Feb. 2019
  • Distributed polarization of sensorimotor cortex by tDCS modulates functional population coding in macaques., Computational and Systems Neuroscience 18 (COSYNE), Lisbon, Portugal, Feb. 2019
  • Signatures of low-dimensional neural predictive manifolds., S. Recanatesi, M.Farrell, G. Lajoie, S. Deneve, M. Rigotti, E. Shea-Brown, Computational and Systems Neuroscience 18 (COSYNE), Lisbon, Portugal, Feb. 2019
  • Correlation-based model of artificially induced plasticity in motor cortex by a bidirectional Brain-Machine Interface, Guillaume Lajoie, Nedialko Krouchev, John F. Kalaska, Adrienne Fairhall, Eberhard E. Fetz, accepted at PLoS Comput. Biol., (2017) Vol. 13, No. 2, pages e1005343, DOI: 10.1371/journal. pcbi.1005343 [Available here]
  • Rewiring cortical circuits: a predictive model of a bidirectional brain-computer interface., G. Lajoie, A. Fairhall, E. Fetz, International Conference on Mathematical Neuroscience, Boulder, CO, May 2017
  • Encoding in Balanced Networks: Revisiting Spike Patterns and Chaos in Stimulus-Driven Systems ,Guillaume Lajoie, Kevin K. Lin, Jean-Philippe Thivierge and Eric Shea-Brown, PLoS Comput. Biol., (2016), Vol. 12, No. 12, Pages e1005258-30, DOI: 10.1371/journal.pcbi.1005258 [Available here]
  • Dynamic signal tracking in a simple V1 spiking model, Guillaume Lajoie, Lai-Sang Young, Neural Computation, (2016), Vol. 28, No. 9, Pages 1985-2010 [Available here]
  • Driving reservoir models with oscillations: a solution to the extreme structural sensitivity of chaotic networks, Philippe Vincent-Lamarre, Guillaume Lajoie, Jean-Philippe Thivierge,J Comput Neurosci, (2016), DOI: 10.1007/s10827-016-0619-3 [Available here]
  • [Featured Talk] Revisiting chaos in recurrent networks: encoding with spikes., G. Lajoie, E. Shea-Brown, International Conference on Mathematical Neuroscience, Antibes, France, May 2016
  • Correlation-based model of a bidirectional Brain-Machine Interface: artificially induced plasticity in motor cortex., G. Lajoie, A. Fairhall, E. Fetz, Computational and Systems Neuroscience 16 (COSYNE), Salt-Lake City, UT, Feb. 2016
  • Structured chaos shapes spike-response noise entropy in balanced neural networks, Guillaume Lajoie, Jean-Philippe Thivierge and Eric Shea-Brown, Frontiers in Computational Neuroscience, (2014), 8:123. [Available here].
  • Encoding and discrimination of multi-dimensional signals using chaotic spiking activity., G. Lajoie, K.K. Lin, J.P. Thivierge, E. Shea-Brown, Computational and Systems Neuroscience 15 (COSYNE), Salt-Lake City, UT, Feb. 2015
  • Structured chaos shapes neuronal spike-response noise entropy of driven balanced networks., G. Lajoie, J.P. Thivierge, E. Shea-Brown, Computational and Systems Neuroscience 14 (COSYNE), Salt-Lake City, UT, Feb. 2014
  • Chaos and reliability in balanced spiking networks with temporal drive, Guillaume Lajoie, Kevin K. Lin and Eric Shea-Brown, Phys. Rev. E, (2013), Vol. 8, No. 5, pp. 052901 [Available here]
  • [Featured talk]Structured chaos and spike responses in stimulus-driven networks., G. Lajoie, K.K. Lin, E. Shea-Brown, Computational and Systems Neuroscience 13 (COSYNE), Saly-Lake City, UT, Feb. 2013
  • Reliable and Unreliable spike times in sparsely connected networks., G. Lajoie, K.K. Lin, E. Shea-Brown, Computational and Systems Neuroscience 12 (COSYNE), Saly-Lake City, UT, Feb. 2012
  • Shared inputs, entrainment, and desynchrony in elliptic bursters: from slow passage to discontinuous circle maps, Guillaume Lajoie and Eric Shea-Brown, SIAM Journal of Applied Dynamical Systems, (2011), Vol. 10, No. 4, pp. 1232-1271[Available here]