This repository contains pdf files, code and data from our data science/machine learning journal club.
-
ML101: Some Python Data Science Resources and scikit-learn examples (Romuald Janik)
-
Unsupervised learning - clustering (Jacek Tabor, II UJ)
-
Deep learning and TensorFlow (Elżbieta Richter-Wąs)
-
MapReduce - Hadoop (Piotr Białas)
-
TensorFlow (Maciej Chociej, Google)
-
More on Convolutional Neural Networks (Romuald Janik)
-
Generative Adversarial Networks. Overview and applications (Rafał Cycoń, FORNAX)
-
The Unreasonable Effectiveness of RNN: an introduction to recurrent neural networks (Przemek Witaszczyk)
-
Introduction to ICA (Jacek Tabor, II UJ)
-
Data Science with Python (Piotr Białas)
-
Introduction to Reinforcement Learning (Rafał Józefowicz, OpenAI)
-
Binary classifiers and receiver operating characteristic curves (ROC curve) (Piotr Białas)
-
A recipe for simple effective models (Michael Abbott)
-
Criticality and Deep Learning (Przemek Witaszczyk)
-
"Fornax.ai and ESA "Data Adventures" hackaton and what we have learned" (Piotr Warchoł, Przemek Witaszczyk)
-
Deep Neural Networks and the Information Bottleneck method (Piotr Warchoł) [M.Kac Seminar]
-
Variational autoencoders (Igor Podolak, II UJ)
-
Mastering the game of Go without human knowledge (Piotr Białas)
-
A multi-instance deep neural network classifier: application to Higgs boson CP measurement (Piotr Białas)
-
Pushing state-of-the art in transcriptomics and metagenomics on the road to personalized medicine (Paweł Łabaj, Bioinformatics Research Group)
-
The input-output Jacobian and initialization of neural networks - our contribution for ResNets and some earlier results (Piotr Warchoł)
-
Deep processing of structured data (Aleksandra Nowak and Łukasz Maziarka, II UJ)
-
Adversarial Examples (Piotr Białas)
-
Improving convergence of stochastic gradient descent (Jarek Duda, II UJ)
-
Contrastive model explanations, an overview (Wojciech Sobala, IBM)