Matthew RoosinTowards Data ScienceUsing null samples to shape decision spaces and defend against adversarial attacksA more naturalistic approach to model trainingFeb 25, 20201Feb 25, 20201
Matthew RoosinTowards Data ScienceEvolutionary approaches towards AI: past, present, and futureCan Darwinism revolutionize AI?Oct 5, 20192Oct 5, 20192
Matthew RoosinTowards Data ScienceRecurrence in biological and artificial neural networksRecurrence is an overloaded term in the context of neural networks, with disparate colloquial meanings in the machine learning and the…May 16, 20192May 16, 20192
Matthew RoosinTowards Data ScienceDeep Learning versus Biological Neurons: floating-point numbers, spikes, and neurotransmittersIn recent years, “deep learning” AI models have often been touted as “working like the brain,” in that they are composed of artificial…Mar 14, 20192Mar 14, 20192