Valentina Giunchiglia
@valegiunca.bsky.social
PhD student at Imperial College London.
Visiting Researcher at Harvard University
Multimodal foundation models for precision medicine
Visiting Researcher at Harvard University
Multimodal foundation models for precision medicine
Reposted by Valentina Giunchiglia
The organisation and scientific advisory committees: @simofoti.bsky.social, @valegiunca.bsky.social, @pragya-singh.bsky.social, @daniel-platt.bsky.social, Vincenzo Marco De Luca, Massimiliano Esposito, Arne Wolf, Zhengang Zhong, Rahul Singh
March 11, 2025 at 3:25 PM
The organisation and scientific advisory committees: @simofoti.bsky.social, @valegiunca.bsky.social, @pragya-singh.bsky.social, @daniel-platt.bsky.social, Vincenzo Marco De Luca, Massimiliano Esposito, Arne Wolf, Zhengang Zhong, Rahul Singh
Apply by the 16th February!
If you have any specific questions, contact: logml.committee@gmail.com
If you have any specific questions, contact: logml.committee@gmail.com
LOGML 2025
London Geometry and Machine Learning Summer School, July 7-11 2025
www.logml.ai
February 2, 2025 at 12:58 PM
Apply by the 16th February!
If you have any specific questions, contact: logml.committee@gmail.com
If you have any specific questions, contact: logml.committee@gmail.com
We are currently recruiting mentors to lead up to 6 students on a week-long project at the intersection of geometry and ML. Mentors can be PhD students (not first years), Postdocs or lectures! Many projects result in top conferences and journal publications. Mentors expenses will be covered.
LOGML 2025
London Geometry and Machine Learning Summer School, July 7-11 2025
www.logml.ai
February 2, 2025 at 12:58 PM
We are currently recruiting mentors to lead up to 6 students on a week-long project at the intersection of geometry and ML. Mentors can be PhD students (not first years), Postdocs or lectures! Many projects result in top conferences and journal publications. Mentors expenses will be covered.
Reposted by Valentina Giunchiglia
December 13, 2024 at 12:13 PM
We tested it on 12 online tasks collected with Cognitron.
Compared to standard measures of RT and accuracy, IDoCT's measures of ability:
- have more interpretable latent cognitive factors
- are less sensitive to device
- have higher sensitivity and specificity
Compared to standard measures of RT and accuracy, IDoCT's measures of ability:
- have more interpretable latent cognitive factors
- are less sensitive to device
- have higher sensitivity and specificity
December 13, 2024 at 12:13 PM
We tested it on 12 online tasks collected with Cognitron.
Compared to standard measures of RT and accuracy, IDoCT's measures of ability:
- have more interpretable latent cognitive factors
- are less sensitive to device
- have higher sensitivity and specificity
Compared to standard measures of RT and accuracy, IDoCT's measures of ability:
- have more interpretable latent cognitive factors
- are less sensitive to device
- have higher sensitivity and specificity
We tested the model on simulated data and IDoCT could reliably recover ground truth measures of trial’s difficulty, ability and visuomotor delay
December 13, 2024 at 12:13 PM
We tested the model on simulated data and IDoCT could reliably recover ground truth measures of trial’s difficulty, ability and visuomotor delay
IDoCT comes with a nice set of features:
- Robust: Works with as little as 100 participants
- Efficient: Scales up inexpensively to > 100K participants
- Flexible: Can work with potentially any online task collecting trial-by-trial responses
- Robust: Works with as little as 100 participants
- Efficient: Scales up inexpensively to > 100K participants
- Flexible: Can work with potentially any online task collecting trial-by-trial responses
December 13, 2024 at 12:13 PM
IDoCT comes with a nice set of features:
- Robust: Works with as little as 100 participants
- Efficient: Scales up inexpensively to > 100K participants
- Flexible: Can work with potentially any online task collecting trial-by-trial responses
- Robust: Works with as little as 100 participants
- Efficient: Scales up inexpensively to > 100K participants
- Flexible: Can work with potentially any online task collecting trial-by-trial responses
IDoCT derives specific estimates of ability, and visuomotor delay from trial-by-trial measures of reaction time (RT) and accuracy, while also providing data-driven trial’s difficulty scales that detect the most challenging aspects/dimensions of each task
December 13, 2024 at 12:13 PM
IDoCT derives specific estimates of ability, and visuomotor delay from trial-by-trial measures of reaction time (RT) and accuracy, while also providing data-driven trial’s difficulty scales that detect the most challenging aspects/dimensions of each task