Facebook researchers announced its face recognition model DeepFace. It shows a very close performance to human level. Humans have 97.53%…
Dance Moves of Deep Learning Activation Functions
Neither convolution nor recurrent layers of deep learning enable non-linearity. Activation functions enable neural networks to become non-linear. An activation…
Attractiveness Score Prediction with Deep Learning
We’ve recently mentioned beauty score prediction. However, that study is mainly based on the study of South China University of…
A Step by Step Perceptron Example
Perception is everything. Communication faculty students learn this in their early lessons. Machine learning practitioners learn this in their freshman…
Beauty Score Prediction with Deep Learning
Remember the famous quote in the Snow White. Evil Queen asks to the mirror on wall that who is the…
A Gentle Introduction to Feature Importance in Machine Learning
Machine learning interpretability and explainable AI are hottest topics in data world nowadays. Even though linear regression is ignored by…
Race and Ethnicity Prediction in Keras
We’ve mentioned how to predict the identity, emotion, age and gender with deep learning in previous posts. Ethnicity and race…
Race and Ethnicity Prediction In The Perspective of AI Ethics
We can predict the demographic and cultural information of people including identity, age and gender, ethnicity based on their photos already.…
Why You Should Build XGBoost Models Within H2O
XGBoost triggered the rise of the tree based models in the machine learning world. It earns reputation with its robust…
A Gentle Introduction to XGBoost for Applied Machine Learning
XGBoost is firstly introduced in 2016 by Washington University Professors Tianqi Chen and Carlos Guestrin. Even though XGBoost appears in an…
