Skip to content
View Caselles's full-sized avatar
69 followers · 23 following

Achievements

Achievement: StarstruckAchievement: Arctic Code Vault Contributor

Achievements

Achievement: StarstruckAchievement: Arctic Code Vault Contributor

Organizations

@obvious-research

Block or report Caselles

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
Caselles/README.md

Hugo Caselles-Dupré.

Research Director at Obvious Research since 2023, in partnership with ISIR (Sorbonne University). I'm also an artist of Obvious, a collective interested in Art & Machine Learning. You can learn more about us here. Currently leading Obvious Research, a research laboratory on Generative AI (image, video, sound) in partnership with ISIR (Sorbonne University). We have an ANR grant of over 1M€ to invent new AI algorithms for artistic creation (2023-2027). We are hiring interns, postdocs, research engineers and PhDs, contact me!

In 2021-2023, I did a Post-Doc at ISIR (Sorbonne University) under the supervision of Olivier Sigaud and Mohamed Chetouani, studying the teachability of autonomous agents. In 2021, I graduated with a PhD from the Flowers Laboratory of ENSTA ParisTech and INRIA (supervised by David Filliat and Michaël Garcia-Ortiz). The title of my thesis is "On the Role of Action and Machine Learning in Artificial Agent Perception".

Pinned Loading

  1. NeurIPS19-SBDRL NeurIPS19-SBDRL Public

    Code for NeurIPS 2019 paper: "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by H. Caselles-Dupré, M. Garcia-Ortiz and D. Filliat.

    Python 35 11

  2. deezer/w2v_reco_hyperparameters_matter deezer/w2v_reco_hyperparameters_matter Public

    Repository to reproduce results of "Word2vec applied to Recommendation: Hyperparameters Matter" by H. Caselles-Dupré, F. Lesaint and J. Royo-Letelier. The paper will be published on the 12th ACM Co…

    Python 53 16

  3. paper_notes paper_notes Public

    Paper notes for my PhD on Machine Learning (mostly focused on Reinforcement Learning)

    16 1

  4. TLESORT/Generative_Continual_Learning TLESORT/Generative_Continual_Learning Public

    Python 53 13

  5. graph_kernels graph_kernels Public

    Four of the main kernels on graphs Python implementation.

    Python 16 1

  6. Deep_Q-Network Deep_Q-Network Public

    Implementation of DeepMind's Deep Q-Network for Reinforcement Learning on OpenAI Gym, using Python with Keras.

    Jupyter Notebook 2