{"id":1964,"date":"2019-09-20T03:52:23","date_gmt":"2019-09-20T03:52:23","guid":{"rendered":"http:\/\/kusuaks7\/?p=1569"},"modified":"2024-04-02T11:51:01","modified_gmt":"2024-04-02T11:51:01","slug":"what-is-ai-a-simple-guide-to-machine-learning-neural-networks-deep-learning-random-forests","status":"publish","type":"post","link":"https:\/\/www.experfy.com\/blog\/ai-ml\/what-is-ai-a-simple-guide-to-machine-learning-neural-networks-deep-learning-random-forests\/","title":{"rendered":"What is AI? A simple guide to machine learning, neural networks, deep learning and random forests!"},"content":{"rendered":"\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhat is AI? Information Age has created a simple guide to AI, machine learning, neural networks, deep learning and random forests.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tArtificial intelligence or AI, the phrase\/acronym gets banded about an awful lot. Unfortunately, a lot of companies that say they use AI don\u2019t. It\u2019s a marketing gimmick \u2014 maybe they are even targeting shareholders, trying to push up their share price. In fact, many experts in AI don\u2019t even like the term, they much prefer to use the words machine and learning, or ML. Delve deeper, and you come across many more terms, neural networks, deep learning, natural language processing and random forests. So what is AI, exactly?\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMarc Warner<\/a>, CEO at\u00a0Faculty<\/a>\u00a0and member of the UK\u2019s\u00a0AI Council<\/a>, gave Information Age what he called a colloquial definition of what AI is \u2014 one that the layman can use. \u201cArtificial intelligence, or AI, is the field of research that seeks to get computers to do things that are considered intelligent when done by humans or animals.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThere are more technical definitions, of course.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\u201cIntelligence is the property of an agent that allows it to optimise the environment,\u201d said Marc. So artificial intelligence builds upon that.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe trouble is, to a lot of people, the phrase artificial intelligence conjures up images of machines, ruling the world, of a naked Arnold Schwarzenegger coming back from the future to stop Sarah Connor.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe reality is very far from this vision of science fiction.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWhich brings us to the reason many experts prefer the term machine learning to artificial intelligence.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

What is the difference between machine learning and artificial intelligence?<\/h2>\n <\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMarc Warner has a nice explanation \u2014 that helps clarify the difference between AI and machine learning.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tUp to the late 1990s, from say 1955 to 1995 \u201cthe majority of researchers thought that the way you\u2019re going to be able to achieve intelligent performance and tasks was to create a load of rules.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSo for example, \u2018this is a cup, this is a table,\u2019. The trouble is, it is extremely difficult to define exactly what a cup or table is.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tOr take another example,\u00a0Falon Fatemi,<\/a>\u00a0founder of\u00a0Node<\/a>,\u00a0draws a parallel with a raccoon.<\/a>\u00a0We all know, intuitively what a raccoon is. When we define a raccoon to children, we don\u2019t outline a set of rules, instead we might show them a picture, or better still a video \u2014 their brain does the rest.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nMarc Warner said that getting computers to recognise a cup proved to be an almost impossible challenge \u2014 what they called the \u2018grounding problem\u2019. It didn\u2019t really get solved until machine learning, \u201cwhich was basically when they, said, \u2018screw it, we are not going to put in explicit rules\u2019. We\u2019re just going to show cups and 1000 saucers and 1000, bottles, and let it work it out itself.\u201d\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe form of AI that used rules describes the Deep Blue IBM computer that famously defeated Gary Kasparov at chess.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tAlthough, intriguingly, Kasparov argued that there was nothing intelligent about Deep Blue \u2014 \u201cit is as intelligent as an alarm clock,\u201d he claimed.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tBut then Kasparov went on to argue that there is nothing especially intelligent about being able to play chess \u2014 humble words from one of the greatest chess players ever. But maybe there is something quite profound in those words \u2014 things only seem to require intelligence until we can work out how to do them.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMachine learning, by contrast to the rules method of applying artificial intelligence, entails training an algorithm on data \u2014 that way it learns.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe key here is the quality of data.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThis also opens up the can of worms that is bias and machine learning, but that is a discussion for another day.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSo machine learning, then, is just one application of AI, but it happens to be just about the only version that has any real relevance today.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMachine learning is proving to be invaluable in areas such as marketing, health care and autonomous cars.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Neural networks and deep learning<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tIf machine learning is an aspect of artificial intelligence, then deep learning is an aspect of machine learning \u2014 furthermore, it is a form of machine learning that applies neural networks.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe idea behind neural networks is to apply a way of learning that mirrors how the human brain works. The human brain is made up of neurons, and these neurons connect with each other via chemical reactions forming synapses.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThere is one big difference with the human brain and that relates to scale. There are in excess of 100 billion neurons in a human brain, and there are trillions of synapses. Neural networks are not even at a tiny fraction of that scale.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFurthermore, the strength of synapses can vary enormously \u2014 quite different from digital technology where there is either a link between neurons, or no link. This effectively provides the human brain with perhaps an infinite number of potential links between neurons.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSo neural networks are not at that level and the analogy with the brain, even a scaled down version, is far from precise.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tMarc Warner says that neural networks are biologically inspired \u2014 and although neural networks are nowhere near the complexity of the brain, he says that we do have a pretty good understanding of how neurons can process images \u2014 in that one area, we may be getting close.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tNeural networks themselves really started to emerge as a viable application in AI when researchers figured out how to use GPUs<\/a>\u00a0\u2014 graphics processor units \u2014 as the individual units, or nodes, or neurons in a neural network.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nSo actually, it was a form of convergence \u2014 it turned out that technology developed for one purpose \u2014 graphics processing \u2014 had applications in artificial intelligence.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tThe late 2010s saw a number of innovations. 2009 saw what has become known as the big bang of neural networks, when Nvidia, a hardware company that originally specialised in technology for video games, trained its GPUs in neural networks. At around that time, Andrew Ng, worked out that by using GPUs in a neural network could increase the speed of deep learning algorithms 1,000 fold.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tDescribing the latest in neural networks, Marc Warner puts it this way: \u201cthey\u2019re enormous beasts\u2026 they have say 150 different pieces, and each piece contains multiple layers.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nEach layer might then be given a specific task, typically they start by identifying edges \u2014 one might identify vertical edges, another horizontal and another curves. From this, another layer can pull this information together to identify say a face \u2014 or a racoon.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFalon Fatemi takes this a step further, talking about what Node calls unsupervised deep learning \u2014 \u201cUnsupervised models can essentially be trained on the knowledge that exists on the web,\u201d she says. \u201cThat we could never as humans digest and read. There\u2019s more information created in a single day than we could possibly absorb in a lifetime, but a machine can absolutely digest it, learn from it, understand it, and dynamically build knowledge of the world that we can then leverage.\u201d\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSo deep learning is a subset of machine learning that applies neural networks, and machine learning is a subset of artificial intelligence.\n\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t
\n\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Random Forests<\/h4>\n<\/h4>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tRandom forests are another subset of machine learning.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tRandom Forests build upon decision trees. A decision tree is a simple method of making a decision which we all intuitively understand.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\u2018Shall I play tennis today?\u2019\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\n\u2018Do I have the time?\u2019\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\u2018If yes, is the weather appropriate?\u2019\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nIf yes, can I get a tennis court?\u2019\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tTurn these decisions into a diagram and you see branches \u2014 bit like a tree, although the word \u2018bit\u2019 seems rather appropriate.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tRandom Forests apply this at scale, applying the concept of wisdom of crowds.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tSupposing you play a game of chance in which the odds are 60\/40 in favour of you wining. Play the game once and there is a 40% chance you will lose. Play the game 100 times and it is highly likely you will win 60 times. And also win overall.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t
\n\t\t\t
<\/div>\t\t<\/div>\n\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tBut then you can go to another level. If you divide playing the game 100 times into say a set, and you play say 100 sets, then you are likely to win the vast majority of those sets.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\nRandom Forests can be applied to machine learning \u2014 for example, with autonomous cars, what decision process should the algorithm apply if it is about to crash in order to minimise damage, or risk of injury?\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tFor example, this paper looks at\u00a0applying random forests to classify images<\/a>, while\u00a0this paper<\/a>\u00a0looks at an algorithm for developing driving skills using random forests.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t

Some other terms<\/h2><\/h2>\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t
\n\t\t\t\t
\n\t\t\t\t\t\t\t\t\tWe will be looking at natural language processing and Monte Carlo simulations in articles to follow.\t\t\t\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t<\/section>\n\t\t\t\t<\/div>\n\t\t","protected":false},"excerpt":{"rendered":"

What is AI? Information Age has created a simple guide to AI, machine learning, neural networks, deep learning and random forests. Artificial intelligence or AI, the phrase\/acronym gets banded about an awful lot. Unfortunately, a lot of companies that say they use AI don\u2019t. It\u2019s a marketing gimmick \u2014 maybe they are even targeting shareholders,<\/p>\n","protected":false},"author":442,"featured_media":4002,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"content-type":"","footnotes":""},"categories":[183],"tags":[97],"ppma_author":[2975],"class_list":["post-1964","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-ai-ml","tag-artificial-intelligence"],"authors":[{"term_id":2975,"user_id":442,"is_guest":0,"slug":"michael-baxter","display_name":"Michael Baxter","avatar_url":"https:\/\/secure.gravatar.com\/avatar\/?s=96&d=mm&r=g","user_url":"","last_name":"Baxter","first_name":"Michael","job_title":"","description":"Michael Baxter is Editor of Information Age<\/a>, Author, and economics and technology writer. He is also an accomplished public speaker, has spoken on disruptive technology, the economy, and Brexit at various locations in the UK and the US and facilitated conferences on GDPR and digital marketing."}],"_links":{"self":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1964","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/users\/442"}],"replies":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/comments?post=1964"}],"version-history":[{"count":5,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1964\/revisions"}],"predecessor-version":[{"id":36546,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/posts\/1964\/revisions\/36546"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media\/4002"}],"wp:attachment":[{"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/media?parent=1964"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/categories?post=1964"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/tags?post=1964"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/www.experfy.com\/blog\/wp-json\/wp\/v2\/ppma_author?post=1964"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}