2nd Project of Course 'Machine Learning' of the SMARTNET programme. Taken at the National and Kapodistrian University of Athens.
-
Updated
Feb 28, 2020 - Python
2nd Project of Course 'Machine Learning' of the SMARTNET programme. Taken at the National and Kapodistrian University of Athens.
Фреймворк глубоко обучения на Numpy, написанный с целью изучения того, как все работает под "капотом".
A web app where user can draw Bengali digit and the AI model can detect handwritten digit and predict the digit.
Neural Network aided diagnosis of Schizophrenia via patient-centered text Data
Manual pure scratch code of Convolution-Pooling-Dropout
Deep Networks with Stochastic Depth for PyTorch
A suite of the generalization-improvement techniques Stroke, Pruning, and NeuroPlast
Covid-19 | Quantifying Uncertainty in Blood Oxygen Estimation Models from Real-World Data
Machine learning Algorithms for the Prediction of Successful Aging in Older Adults
In this repository, I put into test my newly acquired Deep Learning skills in order to solve the Kaggle's famous Image Classification Problem, called "Dogs vs. Cats".
Pytorch implementation of Adaptative Dropout a.ka Standout.
Lightweight library to build and train neural networks in Theano
Convoluted Neural Network for classifying the FashionMNIST data set. Recognition of multiple clothing objects on the same picture with noise using the trained model and OpenCV.
Wasserstein dropout (W-dropout) is a novel technique to quantify uncertainty in regression networks. It is fully non-parametric and yields accurate uncertainty estimates - even under data shifts.
📄 Official implementation regarding the paper "Fine-Tuning Dropout Regularization in Energy-Based Deep Learning".
[PAKDD 2022] Auxiliary Local Variables for Improving Regularization/Prior Approach in Continual Learning
Fraternal Dropout (Research)
Add a description, image, and links to the dropout topic page so that developers can more easily learn about it.
To associate your repository with the dropout topic, visit your repo's landing page and select "manage topics."