For quite some time I was observing the most annoying behavior in Facebook. Some words in chat and in comments were magically changing as I was writing them, creating the most embarrassing typos. It was literally impossible to write some words; they changed the moment I typed the next character, space or question mark. When I went back and fixed the typo, it changed right back. The problem manifested itself only on MS Edge; Chrome didn’t change anything. There are several questions about this in the Facebook support forum, but none of them is answered.

After spending hours looking for some sort of a solution to this ultra-frustrating issue, I finally found it:

It’s not Facebook driving me mad, it’s the default, horribly flawed spellchecker of Windows 10!

If you suffer from the same problem, here’s a quick and simple solution:

Just hit the window button and type “Typing settings”. In the settings panel that appears, switch off everything related to spellchecking.

Boom, problem gone 🙂


Home – Welcome to MLBox’s official documentation — MLBox Documentation

MLBox is a powerful Automated Machine Learning python library. It provides the following features:

Fast reading and distributed data preprocessing/cleaning/formatting.
Highly robust feature selection and leak detection.
Accurate hyper-parameter optimization in high-dimensional space.
State-of-the art predictive models for classification and regression (Deep Learning, Stacking, LightGBM,…).
Prediction with models interpretation.


ryanjay0/miles-deep: Deep Learning Porn Video Classifier/Editor with Caffe

Using a deep convolutional neural network with residual connections, Miles Deep quickly classifies each second of a pornographic video into 6 categories based on sexual act with 95% accuracy. Then it uses that classification to automatically edit the video. It can remove all the scenes not containing sexual contact, or edit out just a specific act.


xgboost-node

XGBoost-Node is the first port of XGBoost to run existing XGBoost model with Node.js.

XGBoost is a library from DMLC. It is designed and optimized for boosted trees. The underlying algorithm of XGBoost is an extension of the classic gbm algorithm. With multi-threads and regularization, XGBoost is able to utilize more computational power and get a more accurate prediction.


surikov/webaudiofont: Use full GM set of musical instruments to play MIDI and single sounds or effects. Support for reverberation and equaliser. No plugins, no Flash. Pure HTML5 implementation compatible with desktop and mobile browser. See live examples.

Use full GM set of musical instruments to play MIDI and single sounds or effects. Support for reverberation and equaliser. No plugins, no Flash. Pure HTML5 implementation compatible with desktop and mobile browser.


SmoothGrad

When a machine learning model makes a prediction, often times we would like to determine which features of the input (pixels, for images) were important for the prediction. If the model makes a misprediction, we might want to know which features contributed to the misclassification. We can visualize the feature importance mask as a grayscale image with the same dimensions as the original image with brightness corresponding to importance of the pixel.


Auto-Keras

Auto-Keras is an open source software library for automated machine learning (AutoML). It is developed by DATA Lab at Texas A&M University and community contributors. The ultimate goal of AutoML is to provide easily accessible deep learning tools to domain experts with limited data science or machine learning background. Auto-Keras provides functions to automatically search for architecture and hyperparameters of deep learning models.

Load More