Take a look at this diagram the picture on the top left is the data set the data is classified into two categories red and blue data is hypothetical however it could represent almost anything coin weights and their diameters the number of petals on a plant and their width clearly there are some definite groupings here everything in the upper left belongs to the red category and the bottom right is blue however.

In the middle there is some crossover if you get a new previously unseen sample which fits somewhere in the middle does it belong to the red category or the blue category the other images show different algorithms and how they attempt to categorize a new sample if the new sample lands in a white area then it means it can’t be classified method the number on the lower right shows the classification accuracy one of the buzzwords that we hear from companies like Google and Facebook is neural net.

A neural net is a machine learning technique modeled on the way neurons work in the human brain the idea is that given a number of inputs the neuron will propagate a signal depending on how it interprets those inputs in machine learning terms it is done by matrix multiplication along with an activation function the use of neural networks has increased significantly in recent years and the current trend is to use deep neural networks with several layers of interconnected neurons.

During Google i/o 2015 during the keynote it was explained how much machine learning and deep neural networks are helping Google fulfill its core mission to organize the world’s information and make it universally accessible and useful to that end you can ask Google now things like how do you say Kermit the Frog in Spanish and because of neural networks Google is able to do voice recognition natural language processing and translation currently.

Google is using 30 layer neural nets which is quite impressive as a result of using these neural networks Google’s error rate for speech recognition has dropped from 23% in 2013 to just 8% in 2015 so we know that companies like Google and Facebook use machine learning to help improve their services .

So what can be achieved with machine learning one interesting area is picture annotation here the machine is presented with a photograph and asked to describe it here are some examples of machine generated annotations the first two are quite accurate although.

I’m not sure there’s a sink in that first picture and the third is interesting in that the computer managed to detect the box of donuts but it misinterpreted the other pastries as a cup of coffee what is it it’s a banana no it isn’t try again what is it it’s a banana no it isn’t what is say it’s an orange this is an orange of course the algorithms can also get it completely wrong look at this first picture those men in hard hats seem to be doing some work however the computer thinks they’re lounging around in a couch and that motor scooter doesn’t look like a fire hydrant to me and I don’t think that horse will be very happy as being described as a surfboard it’s a small off-duty Czechoslovakian traffic warden.

Another example is teaching machines how to write Cleveland amore an American author reporter and commentator once wrote in my days a school taught two things love of country and penmanship now they don’t teach either I wonder what you think about this the above handwriting sample was produced by a recurrent neural network to train the machine its creators are 221 different writers to use a smart whiteboard and copy out some text during the writing the position of their pens was tracked using infrared this resulted in a set of X&Y coordinates which were used for supervised training as you can see from the results they’re quite impressive.

Movie subtitles

in fact the machine can actually write in several different styles and at different levels of untie deenis google recently published a paper about using neural networks as a way to model conversations as part of the experiment the researchers trained the machine using 62 million sentences from movie subtitles as you can imagine the results are quite interesting at one point the machine declares that it’s not ashamed of being a philosopher while later when asked about discussing morality and ethics it said and how

I’m not in the mood for a philosophically debate so it seems if you feed a machine a steady diet of Hollywood movie scripts you get a moody philosopher unlike many areas of AI research machine learning isn’t an intangible target it is a reality that is already working to improve the services we use in many ways it is the unsung hero the uncelebrated star which works in the background trolling through all our data to try to find the answers.

We are looking for and like deep thought from Douglas Adams Hitchhiker’s Guide to the galaxy see sometimes it is the question we need to understand first before we can understand the answer my name is Gary Simms mandrel authority and I hope you’ve enjoyed this video if you did please do give it a thumbs up also please use the comments below to tell me what you think about machine learning also don’t forget to subscribe to Android authorities YouTube channel and as for me I’ll see you in my next video

Hello there my name is Gary Sims from Andrew authority now one area of computing .

That is improving the way we use our smartphones and use the web is machine learning now sometimes machine learning in AI get used interchangeably especially by big brand companies that want to announce their latest innovations however machine learning and AI are quite two distinct areas of computing.

Her of course they are connected and today we’re going to ask ourselves the question Hhat is machine learning the goal of AI is to create a machine that can mimic a human mind and do.

That of course it needs learning capabilities however it’s more than just about learning it’s also that knowledge representation reasoning and even things like abstract thinking machine learning on the other hand is solely focused on writing software that can learn from past experience one thing you might find quite astounding is that in fact.

Machine Learning and Data mining

machine learning is more closely related to data mining and statistics than it is to AI well why is that well first of all we need to look at what we mean by machine learning one of the standard definitions of machine learning as given by Tom Mitchell a professor at Carnegie Mellon University.

Is this a computer program is said to learn from experience II with respect to some class of tasks T and performance measure P if it’s performance at tasks in T as measured by P improves with experience II okay we’ll let me try to put that more simply for you.

If a computer program can improve how it performs a certain task based on past experience then you can say it has learned this is quite different to a program which can perform a task because its programmers have already defined all the parameters and data needed to perform that task.  fFr example a computer program can play tic-tac-toe maybe you call it noughts and crosses because a programmer wrote the code with a built-in winning strategy however a program that has no predefined strategy and only a set of rules about the legal moves will need to learn by repeatedly playing the game until it is able to win this doesn’t only apply to games is also true of programs which perform classification and prediction classification.

Is the process whereby a machine can recognize and categorize things from a data set including from visual data and measurement data prediction known as regression in statistics is where a machine can guess predict the value of something based on previous values for example given a set of characteristics about a house how much is it worth based on previous house sales and this leads us to another definition of machine learning.

It is the extraction of knowledge from data you have a question you are trying to answer and you think the answer is in the data that is why machine learning is related to statistical analysis and data mining machine learning can be split into three categories supervised learning unsupervised learning and reinforcement learning let’s have a look at what they mean supervised learning .

Is where you teach train the machine using data which is well labeled that means that the data is already tagged with the correct answer to correct outcome here is a picture of the letter A this is a flag for the United Kingdom it has three colors one of them is red and so on the greater the data set the more the machine can learn about the subject matter

After the machine is trained its given new previously unseen data and the learning algorithm then uses the past experience to give you an outcome this is the letter A that is the UK flag and so on unsupervised learning is where the machine is trained using a data set that doesn’t have any labels the learning algorithm is never told what the data represents here is a letter but no other information about which letter it is here are the characteristics of a particular flag without naming.

Model about how language works

That flag unsupervised learning like listening to a podcast in a foreign language which you don’t understand you don’t have a dictionary and you don’t have a supervisor or teacher to tell you what you are listening to if you listen to just one podcast it won’t be much benefit to you but if you listen to hundreds of hours of those podcasts your brain will start to form.

A model about how language works you will start to recognize patterns and you’ll start to expect certain sounds when you do get hold of dictionary or a tutor then you will learn that language much quicker reinforcement learning is similar to unsupervised learning in that the training data is unlabeled however when asked a question about the data the outcome will be graded a good example of this.

Is playing games if the machine wins a game then the result is trickled back down through the set of moves to reinforce the validity of those moves this isn’t much due to the computer play just one or two games but if it pays thousands even millions of games .

Then the cumulative effect of the reinforcement will create a winning strategy there are many different techniques for building machine learning systems and many of these techniques are related to data mining and to statistics.

for example if I have a data set which describes different types of coins based on their weight and based on their diameter I am able to use a technique known as nearest neighbor to help classify previously unseen coins with nearest neighbor the new coin is compared to the nearest neighbors around it and see what classification.

They have it’s then given the same classification. as its nearest neighbors now you can pick how many neighbors you want to compare against and that number is often referred to as K so therefore the full title for this algorithm is K nearest neighbors however there are lots of other algorithms that try to do the same thing but using different methods.