The Problem That You're Trying to Solve With Mesin Learning Systems

The problem that you're trying to solve is that the machine is going to spit out sequel that the user didn't write. If you can explain to the user what this sequel is doing, they can more easily determine if it's what they expected or what they need. The accuracy dropis is pretty big, as we ol expect from mesin learning systems. So how to make a model mor robust, not just across toman, across the data base that are very different in the wild? That's still a big open problem,. possibly relating back to the data augmentation problem. Isi ya a, yet, thats stuf, stuff inlay make part of it. Awesome.