AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
Is Deep Learning a Great Fit for Perception Problems?
Deep learning is a great fit for perception problems in general any problem which is naturally amenable to explicit and crafted rules or rules that you can generate by exhaustive search over some program space. I wouldn't read that the space of problems that could be solved with a large neural network was infinite, but it's certainly not out of the question either. The different formulations of the natural language conversation that are less about mimicking and more about maintaining a fun conversation that last for 20 minutes. That's a little less about mimicked and that's more about being able to carry forward a conversation with all the tangents that happen and dialogue and so on. Do you think that problem is learnable with this