I am a Senior Machine Learning Researcher at Prowler.io since February 2018. I hold PhD from the Gatsby Computational neuroscience Unit. I have a broad interest in cognitive science, probabilistic machine learning and approximate inference. In my thesis work, I focused on auditory perception and explored how Bayesian theories of perception could account for various perceptual phenomena revealed in controlled psychophysical experiments. I also developped non-parametric methods for statistical data analysis.



Publications

Journal Papers

  • Lieder I⁺, Adam V⁺, Frenkel O, Jaffe-Dax S, Sahani M, & Ahissar M (2019). Perceptual bias reveals slow-updating in autism and fast-forgetting in dyslexia. Nature neuroscience, 22(2), 256. doi:10.1038/s41593-018-0308-9

  • Chambers C, Akram S, Adam V, Pelofi C, Sahani M, Shamma S, Pressnitzer D (2017) Prior context in audition informs binding and shapes simple features. Nature Communications Nature, 8, 15027. doi:10.1038/ncomms15027

  • Bastian M, Lerique S, Adam ⁠V, Franklin M.S⁠, Schooler J.W, Sackur J (2017) Language facilitates introspection: Verbal mind-wandering has privileged access to consciousness Consciousness & Cognition. doi:10.1016/j.concog.2017.01.002

  • Daunizeau J, Adam V, Rigoux L (2014) VBA: A Probabilistic Treatment of Nonlinear Models for Neurobiological and Behavioural Data. PLoS Comput Biol 10(1): e1003441. doi:10.1371/journal.pcbi.1003441 [code]

Conference Papers

  • Adam V, Eleftheriadis S, Artemev A, Durrande N & Hensman J (2020), Doubly Sparse Variational Gaussian Processes. (to be published in) the Proceedings of the 23rd International Conference on Artificial Intelligence and Statistics.

  • Durrande N, Adam V, Bordeaux L, Eleftheriadis S & Hensman J (2019). Banded Matrix Operators for Gaussian Markov Models in the Automatic Differentiation Era. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics.

  • Adam V, Hensman J, Sahani M (2016). Scalable transformed additive signal decomposition by non-conjugate gaussian process inference. In 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP). [code]

  • Adam V, Structured Variational Inference for Coupled Gaussian Processes. arxiv e-prints 2017 [link][code], Workshop on Advances in Approximate Bayesian Inference, NIPS 2017.

  • Petangoda J, Pascual-Diaz S, Adam V, Vrancx P, Grau-Moya J (2019). Disentangled Skill Embeddings for Reinforcement Learning. Workshop on Learning Transferable Skills, NeurIPS 2019. [link]

Conference Posters

  • Lieder I, Adam V, Sahani M, Ahissar M (2017) Sensory history affects perception through online updating of prior expectations. Cosyne Abstracts 2017, Salt Lake City USA.

  • Adam V, Duncker L, Sahani M (2017) Continuous-time point-process GPFA using sparse variational methods. Cosyne Abstracts 2017, Salt Lake City USA.

  • Adam V, Chambers C, Sahani M, Pressnitzer D (2016) Pre-perceptual grouping accounts for contextual dependence in the perception of frequency shift. Cosyne Abstracts 2016, Salt Lake City USA.

  • Adam V, Soldado-Magraner J, Jitkrittum W, Strathmann H, Lakshminarayanan B, Ialongo A.D, Bohner G, Huh Ben.D, Goetz L, Dowling S, Serban I.V, Louis M (2015) Performance of synchrony and spectral-based features in early seizure detection: exploring feature combinations and effect of latency. International Workshop on Seizure Prediction (IWSP7). Award: Honourable Mention, [report]

  • Adam V, Sahani M (2014) Bayesian perception of the pitch of non-stationary natural sounds. Cosyne Abstracts 2014, Salt Lake City USA.

Talks

  • Doubly Sparse Variational Gaussian Processes, 31st of October 2019, invited talk at the UCL center for Artificial intelligence.

  • Sparse Variational Gaussian Processes, 9th International Congress on Industrial and Applied Mathematics, Valencia, Spain, 17th of July 2019. Symposium on New trends in the developpment of Gaussian process for representing and learning data.

  • Banded Matrix Operators for Gauss-Markov Models in the Automatic Differentiation Era, 20th of November 2018, invited talk at the Max Planck Institute for Intelligent Systems.

  • Scalable transformed additive signal decomposition by non-conjugate gaussian process inference., 2016 IEEE 26th International Workshop on Machine Learning for Signal Processing (MLSP).

  • Sparse Variational Gaussian Processes for Non-Conjugate Latent Factor Models., Janelia Junior Scientist Workshop on Machine Learning and Computer Vision 2017.

Teaching

  • BAMB!: Barcelona Summer School for Advanced Modeling of Behavior, 4th to 10th of September 2019. Teaching assistant. Topics: Introduction to Tensorflow, Model comparison.

  • UCL Graduate School, Dimensionality reduction, Instructor, 2013-2015.

  • UCL Graduate School, Introduction to scientific programming in Python, Instructor, 2014.

  • Gatsby Unit, UCL, Theoretical Neuroscience, Teaching Assistant, 2013.

  • Gatsby Unit, UCL, Probabilistic and Unsupervised Learning, Teaching Assistant, 2013.

  • Gatsby Unit, UCL, Approximate Inference and Learning in Probabilistic Models, Teaching Assistant, 2013.




Education

  • 2012-2017, PhD Candidate at the Gatsby Computational neuroscience Unit. Supervisor: Maneesh Sahani

  • 2009-2011, Master’s Degree in Cognitive Science (Cogmaster), at ENS-EHESS-PARISV, France. Master’s thesis: Study of the implication of cognitive control in adaptation to variable environments (with Etienne Koechlin)

  • 2006-2009, Engineering Diploma at Ecole Centrale de Nantes (France), major: Signal processing.




Projects and other activities

I participated in the development of the scientific application Daydreaming, with financial help from the city of Paris through Science en poche. I started a scientific blog that I plan to revive soon. With the Gatsby Unit we participated in a Kaggle hosted seizure detection challenge and ranked 9/200 and we presented our work at a seizure focused conference. I’ve been involved in consultancy work with the company Swhere applying machine learning techniques to solve business problems.