What is Machine Learning? Is Artificial Intelligence and Machine Learning the same thing?:
In order to answer this question, let us first define what is AI. Artificial Intelligence(AI) term was first coined by American Computer Scientist- John McCarthy and according to him AI is "The science and engineering of making intelligent machines, especially intelligent computer programs".Let me explain it to you in layman's terms it is nothing but the intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Whereas, Machine Learning(ML) refers to systems that can learn by themselves, systems that get smarter and smarter over time without human intervention. Hence, it is evident that ML is a subset of AI and consists of the more advanced techniques and models that enable computers to figure things out from the data and deliver AI applications.
An Overview of Traditional Machine Learning Models:
In this context, traditional means the things that we have been doing for years and is often the foundation for more cutting edge machine learning. There are different models that generally fall into 3 different categories: (1)Supervised Learning, (2) Unsupervised Learning and (3) Reinforcement Learning.
1) Supervised Learning: Input data is called training data and has a known label or result such as spam/not-spam or a stock price at a time.
A model is prepared through a training process in which it is required to make predictions and is corrected when those predictions are wrong. The training process continues until the model achieves a desired level of accuracy on the training data.
Example problems are Classification and Regression.
a) Classification: In this, we need to categorize a certain observation or the object that is under observation in a group. For example, if you are given dots of two different colours i.e blue and red, and you will classify blue and red dots into two different groups based on colour or these red and blue dots can be a symbol for any other observation such as blue dots imply or signify the people that are healthy in a particular sample of people chosen and red dots signify the people that have a certain disease. Example problems are classification and regression.
Few more examples would be — to predict if a given email is spam or not spam? Is a detected particle a Higgs Boson or a normal sub-atomic particle? Assigning a certain news article into a group — like sports, weather, or science. Will it rain today or not? Is this picture a cat or not?
b) Regression: Regression is concerned with modelling the relationship between variables that is iteratively refined using a measure of the error in the predictions made by the model. For example, some businesses use the regression model to forecast their profits in the upcoming months or years, based on the data of the previous profits.
2) Unsupervised learning: Input data is not labelled and does not have a known result. This is useful when there is no example data set with known answers and you are searching for a hidden pattern. In general, unsupervised learning is a bit difficult to implement and thus it’s not used as widely as supervised learning.
Example problems are Clustering and Association rule.
a) Clustering: In this, we group similar things together. For example, a given set of books can be separated or grouped based on its genre. Same goes with news articles. It is somewhat similar to Regression.
b) Association rule: Extract rules that best explain observed relationships between variables in data. For example, it can be a case of a person's preferences like if he buys a product X, he is more likely to buy product Y. Hence, these algorithms are used for market basket analysis using our online or offline retailers shopping data.
3) Reinforcement learning: This strategy is built on observation and trial & error to achieve goals or maximize reward. It is like if a child is supposed to put back a toy in its place, don't tell him to do so, in place of that reward him with a candy or a hug if he keeps the toy back in its place or make a sad face when the child doesn't do what is expected from him. In a similar way, systems are trained by receiving virtual “rewards” or “punishments”, essentially learning by trial and error. Google DeepMind has used reinforcement learning to develop systems that can play games, including video games and board games such as GO.
What is Deep Learning(DL)?
Deep learning is just a subset of Machine Learning(ML). i.e Deep Learning (DL) is ML but applied to large data sets. DL utilizes multi-layer artificial neural networks with many hidden layers stacked one after the other. DL also has somewhat more sophisticated algorithms and requires more powerful computational resources. These are specially designed computers with high-performance CPUs or GPUs. DL is only inspired by the functionality of our brain cells called neurons which lead to the concept of artificial neural networks (ANN). Deep learning has already achieved near or better than human-level image classification, speech/handwriting recognition and of course the autonomous driving and much more. This is just a somewhat basic idea of what DL really is.
Some of the Applications of ML:
1) Virtual Personal Assistants: Everyone must have used Siri or Alexa or Google Assistant at least once in their lifetime. These are the popular Virtual Personal Assistants. As the name suggests, they assist in finding information, when asked over voice. All you need to do is activate them and ask "How Is today's weather?","Where can I find the closest restaurant?" and much more. For answering, your personal assistant looks out for the information, recalls your related queries, or sends a command to other resources (like phone apps) to collect information related to what you have asked for. Machine learning is an important part of these personal assistants as they collect and refine the information on the basis of your previous involvement with them. Smart Speakers like Amazon Echo and Google Home also work on the same principle.
2) Traffic Predictions: We have all been using GPS Navigation Services on our phone like Google Maps etc. While we do that, our current locations and velocities are being saved at a central server for managing traffic. This data is then used to build a map of the current traffic and this helps us in preventing the congestion caused due to the traffic.
3) Web Search Engine: One of the reasons why search engines like google, bing etc work so well is because the system has learnt how to rank pages through a complex learning algorithm.
And the list of the application of ML just goes on.
Hence, in my opinion, learning ML is a fundamental step towards the progress of what lies ahead in the future and some of us are yet to find more applications of it.
Nice!
ReplyDeleteThank you for your valuable feedback!
Delete