Machine learning interpretability and explainable AI are hottest topics in data world nowadays. Even though linear regression is ignored by … More
Tag: python
Mish As Neural Networks Activation Function
Recently, Mish activation function is announced in deep learning world. Researchers report that it overperforms than both regular ReLU and Swish. The … More
The Fastest Way to Calculate Combination and Permutation
Combination and permutation calculations appear often in daily programming challenges such as HackerRank. Even though we all know how to … More
Explaining h2o models with Lime
Interpretability and accuracy inversely proportional concepts. Models offering higher accuracy such as deep learning or GBM would be lowly interpretable. … More
A Gentle Introduction to Chefboost for Applied Machine Learning
Even though deep learning is hottest topic in the media, decision trees dominates the real world challenges. Recently, I’ve announced a … More
Face Recognition with OpenFace in Keras
OpenFace is a lightweight and minimalist model for face recognition. Similar to Facenet, its license is free and allowing commercial … More
How Modin Can Keep Data Scientists From Pandas
Data scientists tend to use pandas for data transformation because it is pretty. I witnessed many times that feature engineering … More
Tips and Tricks for GPU and Multiprocessing in TensorFlow
Having a GPU shows the wealth. Today, you should spend thousands of dollars to have a good one. For example, … More
Apparent Age and Gender Prediction in Keras
Computer vision researchers of ETH Zurich University (Switzerland) announced a very successful apparent age and gender prediction models. They both … More
A Gentle Introduction to Edwards-curve Digital Signature Algorithm (EdDSA)
Elliptic curves are the most challenging topic in crypto field whereas Edwards curves are the hottest topic among elliptic curves. Elliptic … More
