mjpekala Goto Github PK

ae-stability-study

Numerical experiments related to AE detection.

bio-segmentation

This repository hosts simple examples of using deep networks to segment electron microscropy and other biological image data.

bio-segmentation-dense

Software for generating dense (i.e. per-pixel) labels using semantic segmentation [lon2015]. The current implementation is based on the U-Net architecture [ron2015].

calibration-example

This repository hosts a small example for calibrating binary classifiers.

cp-lite

A simple bare-bones implementation of a conformal predictor for use in a "batch" setting.

empirical-interpolation

An experiment with the "magic points" mechanism for developing interpolation-based surrogates.

faster-membranes

This repository hosts an experiment for segmenting EM images, with the goal of working more quickly than exhaustive application of CNNs on a per-pixel basis.

gp-am-study

Initial investigations into Gaussian processes for AM.

keras

Deep Learning library for Python. Runs on TensorFlow, Theano, or CNTK.

maxfun-experiment

An empirical study comparing MAXFUN to other feature pooling techniques.

mjpekala.github.io

nips-adversarial-2017

Codes for the NIPS 2017 adversarial example competition.

shearlet-scattering

Scattering transforms with shearlet-based filters.

streetsigns

uq-dropout-experiment