We were all impressed by the smiling face Rosanna drew in the class.It showed us how to describe happy and unhappy using mathematical language as well as the knowledge about machine learning.
Machine learning is a subfield of computer science and statistics that deals with the construction and study of systems that can learn from data, rather than follow only explicitly programmed instructions.
It's all about the question "Can machines do what we (as thinking entities) can do?" In fact, learning algorithm is so powerful that we are unaware of using it everyday. If you use a website like Taobao or Amazon that will often recommend clothes and book to you,these are examples of learning algorithms that have learned what sort of things you like to buy,and can therefore give customized recommendation to you.
Machine learning tasks can be of several forms:Supervised Learning,Unsupervised Learning,Reinforcement Learning.
Machine learning tasks can be of several forms:Supervised Learning,Unsupervised Learning,Reinforcement Learning.
Supervised Learning
The theory mentioned in the class is supervised learning. If we have some documents which we know their sentiment class,we can use them to train a classifier.
Regression problem:
The variable you are trying to predict is a continuous value.
Classification Problem:
The variable you are trying to predict is discrete rather then continuous.It's either 0 or 1,just the same as happy or unhappy.In fact ,more generally,there will be more learning problems where we'll have more than one input variables and features.And one of the most interesting thing is what if you data doesn't lie in a two-dimensional or three-dimensional or even a finite dimensional space.But it's possible what if your data lies in finite dimensional space.It turns out there is a successful classes of machine learning algorithm called support vector machines which actually takes data and maps data to a finite dimensional space.
Learning Theory
It's about how and why learning algorithm works.We try to understand what algorithms can approximate different functions well and also try to understand things like how much training data do you need.If you're trying to design a learning algorithm,should you be spending more time collecting more data or it is the case that you already have enough data so don't have to waste time.
Unsupervised Learning
In an unsupervised learning problem,you're given a dataset without right answer on any of your data.Would you find any interesting structure in this dataset?The clustering algorithm is one example of unsupervised learning.It turns out these sort of unsupervised learning algorithms are also used in many problems--things like organization computing clusters,social network analysis,market segmentation,even for astronomical data analysis.
There is a classical problem called cocktail party problem which use ICA algorithm to separate out interested voice from all this loud background noise.
Reinforcement Learning
This refers to problems where you don't do on-shot decision-making.In reinforcement learning problem,you are usually asked to make a sequence of decisions over time.
I have learnt Artificial Intelligence and Pattern Recognition. They both include similar knowledge like supervised learning, classification and so on. I hope we can have a further communication when free.
回复删除In your blog, I found that you have a good understand about the Machine Learning, and I learnt a lot in your blog. thanks very much about you sharing.
回复删除Thanks for your sharing! I have a clear and deeper understanding of three forms of machine learning tasks. The highlights of lecture is summarized in a very clear and logical way. I will trace your blog and also you are welcome to come to my blog to have some discussion about this course:)
回复删除Classifying of data or not is the key difference between the Unsupervised Learning and supervised learning, isn't it? From your article, supervised learning's data already labelled, and the other is not.
回复删除That's right!You seemed to be very interested in this topic,then you can find some useful online videos provided by other university.Hope we can share more with each other!
删除If people can operate machines effectively and accurately, there is no denying that our future lives will become better!
回复删除Thank you for your sharing! It is really helpful for me to understand what we have learned in the class!
回复删除thanks so much about your sharing, from your blog I have a quick access to review supervised learning and the unsupervised one~
回复删除I like this post because it makes a list of important basic terms in a clear summary. And I think the pictures you use look cute. Thank you for your post!
回复删除From your blog , I have learned some new knowledge and review the one that has been taught. Very useful.Thanks. BTW, it seems now machine learning is really hot topic.On a personal level, to further learning about it is really meaningful.
回复删除I think you must do much research about the recommending system of several platforms.
回复删除and we can find may coding package of a website recommending system, which is the reason why so many websites have the almost same recommending mechanism.
thank for your sharing. Those basic knowledges you mentioned above are all the fundamental of our course. but I think if you can do one of them really good.you will be an expert.
回复删除Thank you for you sharing .In this passage I have known the process of machine learning is similar to that of data mining. Both systems search through data to look for patterns.And machine learning programs detect patterns in data and adjust program actions accordingly.
回复删除