The more that I learn about Deep Learning and other Machine Learning concepts the more intrigued by the idea that we could apply some of things we learn about how these ML models behave back onto human psychology. This is not something I have heard discussed yet. They were, after all, roughly modelled on how our own neurons work and could be considered a crude model of how we work.
What are some of the behaviours and lessons we’ve learned from training AIs that could be applicable to how we learn for example. AIs are obviously dramatic simplifications of our own minds but they learn in similar ways.
Machine learning algorithms can be divided into supervised and unsupervised learning models. They are not equivalent and the things you can do with one are not possible with the other approach. Would it be helpful to identify topics in school that can be associated with each approach so that we can optimise our teaching approaches?
A concrete example of this is how we learn a new language. A common suggestion for language learning is to immerse yourself in it. To that end people will listen to radio and music in their target language. Is that an effective way to improve your understanding? This would be considered mostly unsupervised since we have no answers for what a particular sound we hear might mean (unless we can guess from a context of other words we already know). If we fed 10,000 hours of voice recordings into an unsupervised machine learning algorithm what kind of things would we be able to learn? It might be able to pick up some common words or phrases that are used, it might be able to find words that are often used close together. It would get a feel for the ‘sound’ of a language. But that is likely as deep of an understanding as it could make.
Given this insight we could hypothesis that immersing yourself with just recorded audio is not particular effective at learning what words mean.
If we wanted to teach a computer to hear a word and turn it into text we need to have the sounds and the matching text. This is a supervised approach and can be quite effective. However, we know that this is much more effective if we have lots and lots of training data. For a particular word it helps to have the word spoken by many different people, spoken quickly and slowly, varying pitches and accents. The more examples we have to train on the better the accuracy is going to be. You’ve probably experienced listening to a song and hearing a word you can’t quite make out. You listen over and over but still can’t get it. Then someone else tells you what the lyric is or you hear a different recording of the song and suddenly it becomes crystal clear. Now you can hear it.
Given this, perhaps we could ensure that training programs on a computer don’t just replay the same recorded words over and over again but instead give lots of variations. It would be interesting experiment to have a 1 page story in your target language recorded by 10-20 different people. Would listening and reading along to all the recordings help with your listening comprehension? How much better would you learn listening to 1 recording 20 times vs 20 different recordings?
Several studies have looked at the efficacy of same-language closed captioning to reading and listening comprehension and prove that it can help. Similar application of supervised learning applied to people.
Another area that generates much concern in machine learning is how to identify and prevent over-training. Over training happens when the algorithm essentially memorises the answers and has difficulty applying to new input it hasn’t seen yet. There are techniques for testing that are used to help diagnose over training. One such approach is to separate the training data from the testing data. Trying to determine if students have memorised the answers or really understand a concept is critical to their ability to move forward and build on those lessons. Could we apply our machine approaches to humans to help identify memorisation vs understanding?
I’m sure there are more fascinating ways we could take what we have learned from teaching machines and apply it to how we teach people.