Week 3
Think of a machine learning application and draw a diagram of a neural network, speculating which features the two hidden layers might detect. (see 5:31f in the 3Blue1Brown video) Bonus points if your application does not use camera/vision at all.
This is an audio recognition network I imagine.
What specifically caused the end of the most recent “AI winter”? What, in your opinion, could be a plausible scenario that might lead to the next “AI winter”?
From my perspective, I think it is the rapid development of hardware, especially GPU, ended the recent AI winter (maybe around the 2010s). Because machine learning requires a large amount of computing resources, the hardware before was not powerful enough to do such work.
The next AI winter may be caused by ethical issues. Nowadays, governments are more and more rigid on privacy protection. It may be hard for tech companies to collect training data. The AI may slow down its development due to a lack of training data.
Alone or with a partner, come up with some small application that uses a neural network to do some classification or regression from numeric inputs. See the tutorial for some examples, or reach out to @gohai on Slack if you have questions!
This is a small application that classifies emotions.