Artificial Intelligence: Past, Present, Futures — John Ashmead
From neural nets and genetic algorithms to facial recognition and deep fakes, artificial intelligence (AI) is everywhere today. What exactly do we mean by AI? How did AI get where it is today? What role will it play in our lives? What are the benefits and risks of AI? And when will we have real AI?
Neural network attack vectors — Avani Wildani
Neural networks in the brain are sparsely connected, composed of components with an over 50% failure rate, and still amazingly consistent in their high-level behavior over time. We are building models of biologically plausible neural networks to help explain how the brain can protect against a malicious adversary while keeping networks tiny, low power, and easily trained. Using parameters taken from the somatosensory cortex, we have built a prototype simulator to show the relationships between connectivity and severity of possible attacks.