The perception of novel solutions in engineering is convoluted especially in the context of artificial intelligence (AI). E.g. machine learning is promising to build the next generation of safe, light weight and performant designs solely based on historical datas.
Yet, rightfully the acceptance of these ambitious claims is declining. The AI models’ brittleness, their ’embedded bias’, their sluggishness in working with ‘uncertainties’ and not to forget their innate weakness in math are becoming show stoppers. Rafinex stochastic topology optimizer Möbius is radically different. [further read]