renaudmarquis
Research scientist with special interests in signal processing, data analysis, computational neuroimaging, behavioural sciences and cyber security
CHUVLausanne, Switzerland
Pinned Repositories
conn-viz
OG 2019 - Project 09: Visualizing brain connectomics using D3.js
amld-workshop-pneumonia
Workshop about detecting pneumonia in X-Ray images
conn-viz
OG 2019 - Project 09: Visualizing brain connectomics using D3.js
desktop-app
One app to rule them all!
dual-EEG
Processing and interoperability for dual EEG project
eegdev
Biosignal acquisition device library
eegview
Minimal software to display in realtime and record EEG signals
FIACH
Development version of FIACH
mnelab
MNELAB - a graphical user interface (GUI) for MNE
Pneumonia-Diagnosis-using-XRays-96-percent-Recall
BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.
renaudmarquis's Repositories
renaudmarquis/conn-viz
OG 2019 - Project 09: Visualizing brain connectomics using D3.js
renaudmarquis/amld-workshop-pneumonia
Workshop about detecting pneumonia in X-Ray images
renaudmarquis/desktop-app
One app to rule them all!
renaudmarquis/dual-EEG
Processing and interoperability for dual EEG project
renaudmarquis/eegdev
Biosignal acquisition device library
renaudmarquis/eegview
Minimal software to display in realtime and record EEG signals
renaudmarquis/FIACH
Development version of FIACH
renaudmarquis/mnelab
MNELAB - a graphical user interface (GUI) for MNE
renaudmarquis/Pneumonia-Diagnosis-using-XRays-96-percent-Recall
BEST SCORE ON KAGGLE SO FAR , EVEN BETTER THAN THE KAGGLE TEAM MEMBER WHO DID BEST SO FAR. The project is about diagnosing pneumonia from XRay images of lungs of a person using self laid convolutional neural network and tranfer learning via inceptionV3. The images were of size greater than 1000 pixels per dimension and the total dataset was tagged large and had a space of 1GB+ . My work includes self laid neural network which was repeatedly tuned for one of the best hyperparameters and used variety of utility function of keras like callbacks for learning rate and checkpointing. Could have augmented the image data for even better modelling but was short of RAM on kaggle kernel. Other metrics like precision , recall and f1 score using confusion matrix were taken off special care. The other part included a brief introduction of transfer learning via InceptionV3 and was tuned entirely rather than partially after loading the inceptionv3 weights for the maximum achieved accuracy on kaggle till date. This achieved even a higher precision than before.