Roman TrusovinXIX.ai, Inc.Quantifying the Inherent Bias in Mainstream Facial Recognition TechnologyThe most widely used FR training set is 50+ percent white and 70+ percent male: no wonder FR solutions fail accuracy tests for women and…Apr 24, 2020Apr 24, 2020
Roman TrusovinXIX.ai, Inc.How Adversarial Attacks WorkRecent studies by Google Brain have shown that any machine learning classifier can be tricked to give incorrect predictions, and with a…Oct 16, 20174Oct 16, 20174
Roman TrusovinCube DevText Classifier Algorithms in Machine LearningKey text classification algorithms with use cases and tutorialsJul 12, 20176Jul 12, 20176