The Breadth of Machine Learning

Some useful and in my experience correct ideas.   Its still hard to produce and learn general intelligence.  What worked for us was to be as narrow as possible, with rules or by neurons.   Narrow is also useful too for maintenance, as context expands over time.   You start to lose good understanding of what data must be learned.  Learning about changing scope is important. The example area,  culinary knowledge, is an area of interest of mine.

The AI revolution will be led by toasters, not droids

It’s far easier for software to learn to do one thing well than to be a digital jack of all trades   By Janelle Shane in Fastcompany

Will the intelligent algorithms of the future look like general-purpose robots, as adept at idle banter and reading maps as they are handy in the kitchen? Or will our digital assistants look more like a grab-bag of specialized gadgets–less a single chatty master chef than a kitchen full of appliances?

If an algorithm tries to do too much, it gets in trouble. The recipe below was generated by an artificial neural network, a type of artificial intelligence (AI) that learns by example. This particular algorithm scrutinized about 30,000 cookbook recipes of all sorts, from soups to pies to barbecues, and then tried to come up with its own. The results are, shall we say, somewhat unorthodox:  ... "