AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
How Cold Can Extrapolate in Any Meaningful Way?
The neuron network is only capable of slicing and dicing the impet space with flat planes. The quickest way to make the neural network fit the data is to effectively linearize the data by applying a non linear transformation before it even gets in. But this idea that you don't need feature engineering and neuran networks, i think, is nonsense. It begs the question, how cold possibly extrapolate in any meaningful way? Riht, especially in the general setting.