Skip to content
View annelisesaive's full-sized avatar
  • Lisbon, Portugal

Block or report annelisesaive

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.

Content in all repositories owned by your account will be closed.
Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
annelisesaive/README.md

Hi, I'm Anne-Lise

Applied ML researcher. I build models that recover latent structure from noisy real-world neural, physiological, linguistic and behavioral signals.

Current focus: rigorous evaluation and calibrated inference on messy real-world data. Time-series and language models, honest nulls, abstention over fluency.

Background: PhD, Cognitive Neuroscience (Université Claude Bernard Lyon 1). Tenured Research Scientist at Institut Lyfe. Visiting Researcher at the Champalimaud Foundation (Lisbon). Postdoc at CoCo Lab / UdeM (Mila-affiliated).

Open-source: contributor to NeuroPycon (NeuroImage 2020) and Visbrain (Frontiers in Neuroinformatics 2019).

Selected projects

  • DeepFooding eating-behavior quantification from meal videos. CLIP / X-CLIP / SlowFast, continuous-target bite detection, hierarchical food-type classification.
  • Memorable Scents predictive modeling of odor-evoked memory (RF / XGBoost + SHAP, N=106). iScience 2026.
  • Wine Tasting KG knowledge graph and price-quality analysis on ~130k wine reviews. Powers QualitySip, a Streamlit app for value-for-money wine discovery.
  • Chatbot Wine Memory adaptive dialogue for semi-structured sensory-memory elicitation.

Writing

Flavors of Science a newsletter on flavor, memory, and AI for industry and curious humans.

Elsewhere

LinkedIn · Google Scholar · Substack

Pinned Loading

  1. DeepFooding-CDL DeepFooding-CDL Public

    Eating-behavior quantification from meal videos. Pose and keypoint tracking with confidence-aware post-processing.

    Jupyter Notebook 1

  2. jltt-grc/memorable_scents jltt-grc/memorable_scents Public

    Code and notebooks for the Memorable Scents project: analyzing odor-evoked memories and modeling what makes a scent memorable.

    Jupyter Notebook 2

  3. Wine_tasting_KG Wine_tasting_KG Public

    Knowledge graph + price-quality analysis on 130k wine reviews. Powers QualitySip (Streamlit app for value-for-money wine discovery).

    Jupyter Notebook 1

  4. Chatbot_Wine_Memory Chatbot_Wine_Memory Public

    Adaptive chatbot for semi-structured interviews on memorable sensory experiences. Captures sensory detail, setting, emotion, personal significance

    Python