When you heard these two words you probably think both are same. Well not really, I’ll explain this with a simple definition of two terms. Before start Welcome to first bittribes article. 🙂
Machine learning is a subset of artificial intelligence in the field of computer science that often uses statistical techniques to give computers the ability to “learn” (i.e., progressively improve performance on a specific task) with data, without being explicitly programmed.
– Wikipedia –
Simply it is provide some data and let machine to learn by themselves. At its core, machine learning is simply a way of achieving AI. The name machine learning was coined in 1959 by Arthur Samuel. Evolved from the study of pattern recognition and computational learning theory in artificial intelligence. He defined it as, “the ability to learn without being explicitly programmed.”
Artificial intelligence (AI), sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals.
– Wikipedia –
So AI enables machines being able to perform tasks that are generally characterized as part of human intelligence. This includes things like planning, understanding language, recognizing objects and sounds, learning, and problem-solving.
Basically AI has two categories, General & Narrow. General AI is similar to human intelligence and have all the characteristics. Narrow AI only touches some parts of human intelligence like vision or hearing. They are performing well in the filed they specialized but lack in performance in other AI areas.
Machine Learning based on training an algorithms which can lean how. “Training” means feeding huge amounts of data to the algorithm on specific scenario so algorithm can adjust itself and improve. Simple example is vehicle detection algorithms. First we give thousands of images of vehicles and tag them like vans, cars etc. Then if we give a new picture algorithm can accurately tag it. So this means machine learned “What is car”.
For a simple explanation, one can build AI without machine learning but this may require million lines of coding with complex rules and decision trees. Machine Learning enables programmers to avoid hard-coding and make easy to build on decision taking processes. Other approaches include decision tree learning, inductive logic programming, clustering, reinforcement learning, and Bayesian networks.
Machine Learning and AI are vast topics and an upcoming trend in computer field. We hope to bring more articles on AI, Machine Learning and Neural Networks. Stay with bittribes. Stay touched for next article.