Identification of Autism Spectrum Disorder using ML

The goal of this report is to apply machine
learning algorithms to classify autism spectrum
disorder (ASD) patients and typically developing (TD)
participants using fMRI data from ABIDE dataset.
SVM and KNN were used for classification purpose.
Multi-layer perceptron classifier was also used for
comparison. I used a cross-validation grid search to
fine-tune the hyperparameters for each classifier.
Finally, a stacked ensembled model was used with the
tuned hyperparameters of the classifiers. More information can be found in report.pdf file.