Machine Learning – ML: The current version of machine learning as used in the industry is very limited and it’s dedicated to the completion of mundane tasks only. ML of today in all cases does its work on centralised infrastructure. Though there are some success stories where it also runs exceptionally well on a distributed infrastructure. In machine learning environment or setup, various algorithms and services are managed between the actual source of the data and the learning platform which can be on the cloud. These methods may/may not be at the most efficient but for now, they work well.
In this blog post, I am attempting to create a short text movie of machine learning timelines to give a high-level view on machine learning evolution.
Machine learning has evolved from Artificial Intelligence subset to its own domain (not fully though). It has reached to it an inflexion point – at least in terms of messaging. I remember in my school days as part of statistics class we were told something about AI and ML and we laughed then in the 1990s. Blockchain, quantum computing and wireless connectivity to support IoT on 4G/5G (6G is not very far though) are now norms, not fascinating techs.
The evolution has happened from Turing machines to current very highly intelligent robots. How much machine learning has come far from its origin, difficult to judge and measure but results are clear and visible though. In recent years, the term ‘machine learning‘ has become very popular among developers and business alike, even though research in the field has been going on for 5 decades plus. AILabPage defines machine learning is a simple and easy manner as below.
“A focal point where business, data, experience meets emerging technologies and decides to work together”.
The classic example of ML which we use knowingly or unknowingly on an almost daily basis
- Managing our email box. Each time clicking the “not junk” or “junk” button on a miscategorised email, the machine learns a little bit more.
- Using Siri, Cortana or Google Assistant on smartphones.
These tools become more efficient at usage, actions we take or at each interaction with these technologies. Every time the machine learns from its mistake and adjusts the attributes e.g in case of email system it looks at each email accordingly. In short, the more we torture the data the better the algorithm gets in machine learning.
Machine Learning Approach
The approach of developing ML includes learning from data inputs based on “What has happened”. Evaluating and optimizing different model results remains focus here. As on date Machine Learning is widely used in data analytics as a method to develop algorithms for making predictions on data. It is related to probability, statistics, and linear algebra. Point to not its not just regression or a fancy version of regression.
Machine Learning is classified into three categories at a high level depending on the nature of the learning and learning system.
- Supervised learning: Machine gets labelled inputs and their desired outputs. The goal is to learn a general rule to map inputs to the output.
- Unsupervised learning: Machine gets inputs without desired outputs, the goal is to find structure in inputs.
- Reinforcement learning: In this algorithm interacts with a dynamic environment, and it must perform a certain goal without a guide or teacher.
Today’s machines are learning and performing tasks; that was only be done by humans in the past like making a better judgement, decisions, playing games etc. This is possible because machines can now analyse and read through patterns and remember learnings for future use. Today the major problem is to find resources that are skilled enough to demonstrate & differentiate their learning from university & PhD books in real business rather than just arguing on social media with others.
Primary Goal Of Machine Learning
AILabPage defines machine learning as “A focal point where business, data, experience meets emerging technology and decides to work together”. If you have not unfolded machine learning jargon already then please take look on our machine learning post series library.
Machine learning is the process of a machine attempting to accomplish a task, independent of human intervention, more efficiently and more effectively with every passing attempt i.e learning phase. At this point, AI- a machine which mimics the human mind, is still a pipe dream. In the middle, we have the meat of the pipeline, the model, which is the machine learning algorithm that learns to predict given input data.
Machine Learning is a subset of artificial intelligence where computer algorithms are used to autonomously learn from data and information. Machine Learning, however, has been a reality in our lives for quite some time on the other hand Deep learning is a subcategory of machine learning algorithms that use multi-layered neural networks to learn complex relationships between inputs and outputs.
The most basic rule and meaningful point to understand anything about machine learning are; quality of data it gets served with. So this means its purely driven by data sets to provide answers. It follows the GIGO method. The set of algorithms are as important as underlying data sets.
Machine Learning Evolution
Some of the evolutions, which made a huge positive impact in real-world problem solving, are highlighted in the above picture with title Machine Learning and some use cases There are success stories where organisations have made remarkable progress and value-adds for business with each type of learning. Making the right choice on which ml techniques to be used for a particular business problem requires experience and a thorough understanding.
Each type of machine learning provides a strategic and competitive advantage but the availability of quality data basis which technique is chosen is far more important. Types of machine learning algorithms and which one to be used when is extremely important to know. The goal of any machine learning task and all the things that are being done in the field that puts you in a better position is to break down a real problem in design form for machine learning systems.
ML develop its own encompassing strategy from the experience it comes across over the period of time. Sir Andrew Ng says AI is a new form of electricity so, in my opinion, ML is no different; This has been one of the most active and rewarding areas of research due to its widespread use in many areas. Some of the major breakthroughs in ML includes Natural Language Processing and DeepLearning.
Points to Note:
All credits if any remains on the original contributor only. We have covered all basics around Machine Learning. Machine Learning is all about data, computing power and algorithms to look for information. In the upcoming post, we will cover new type machine learning task under neural network Generative Adversarial Networks. A family of artificial neural networks.
Books + Other readings Referred
- Research through open internet, news portals, white papers and imparted knowledge via live conferences & lectures.
- Lab and hands-on experience of @AILabPage (Self-taught learners group) members.
Feedback & Further Question
Do you have any questions about Supervised Learning or Machine Learning? Leave a comment or ask your question via email. Will try my best to answer it.
Conclusion – Machine Learning is the branch of computer science, unlike statistics which is a graphical branch of mathematics. Though its not entirely true but up to some extent Statistics can be called as graphical branch of mathematics (In my personal opinion). ML deals with the development of computer algorithms that learn and grow themselves. Machine Learning can be very specific task-oriented as well. In a specific environment, a machine can be forced to learn just the rules of a game. It had to try out millions of different strategies for each situation in this case before it prepares self to play against its opponent. For example a game of chess or backgammon.
================ About the Author ===================
Read about Author at : About Me
Thank you all, for spending your time reading this post. Please share your feedback / comments / critics / agreements or disagreement. Remark for more details about posts, subjects and relevance please read the disclaimer.
Categories: Machine Learning