Some of the most exciting technologies evolving in today’s world.
Artificial Intelligence Example
Amazon echo : Amazon echo is a wonderful tool, we can go in there and can say HEY Alexa, what is the temperature in Chicago and the Amazon echo then translates that into zero and ones, something that computer understands then it comes in and processes that information to identify what you are asking and what you need and where to get that information and then it comes back and says the current temperature in Chicago is six degree Fahrenheit or whatever it is at the movement.
So this is the wonderful example of Artificial Intelligence.
Machine Learning Example
Machine Learning example out there is Google, you are on google search engine it comes up you spend a lot of time on the first link you come into and you read the page and google looks at that and says okay he spent five minutes on this, let’s give it a thumbs up, and then you go to the second page and the third page, you just kind of skip over them and glanced at that for a couple of seconds and google says he wasn’t interested in those pages, Let’s give them a thumbs down .
So this is a good example of Machine learning as it starts guessing what you like and what you don’t like, so it gives you more information along which you are going to read and actually use.
Deep Learning Example
- In this example we have a black and white image it comes in two and then we have a neural network, some people like to call it a magic box because it’s hard to follow all that’s going on in there.
- There’s all these different weights and connections and nodes and then it comes out and colors the beach ball, the people, the background.
- What’s going on in here as the black and white image goes this neural network has looked at all these different pictures on the web or whatever it pulls the data from and it’s already itemized them and kind of separated them that we have something that look like beach balls.
- We have something that look like people in a program set, so that when the black and white images comes in, it goes okay that piece right there resembles this all these four other photos.
- The neural network is able to identify that and then color the beach balls with the colors that you see on there, so this is wonderful job, coloring this picture and that’s the full step up is where the deep learning example comes in and the usual center around neural networks.
Human Vs artificial intelligence
Humans are amazing let’s just face it.
We are amazing creatures, we all are over the planet, we are exploring every niche and nook, we have gone to the moon, we got into the outer space we are just amazing creatures, we are able to use the available information to make decisions to communicate with other people, identify patterns and data, remember what people have said adapt to new situations.
Let us look at artificial intelligence VS the human
Artificial intelligence develops computer systems that can accomplish tasks that require human intelligence, so we are looking at this, one of the things that computer can do is they can provide more accurate results.
- This is very important because with AI one is going to give consistent prediction of what’s going to come out interacts with human using their natural language.
- We have seen that is probably the biggest development feature right now that’s in the commercial market that everybody gets to use as we saw with the example of Alexa, they learn from their mistakes and adapt to new environments so we see this loli coming in more and more and they learn from data and automate repetitive learning.
- Repetitive learning has a lot to do with the neural networks, one need to program thousands upon thousand of pictures in there and it’s all automated so as today’s computer evolved it’s very quick and easy and affordable to do this.
What is Machine Learning and Deep Learning all about?
- Imagine, say you had some time to waste, and you are sitting by the road and lot of time passes by there and suddenly you wonder how many cars, buses, trucks and so on passed by in the six hours, and you want to know how many cars, buses, trucks, and so on passed by in the 6 hours?
- So no one is going to sit by the road for six hours and count buses cars and trucks unless you are not working for the city and you are trying to do city planning and you want to know, do we need to add a new truck route, may be we need a bicyclists here that kind of thing, so may be city planning will be great for this.
The way machine works is we have labelled data with features, so you have a truck or a car or a motor cycle or a bus or a bicycle and each one of those are labeled and based on those labels and comparing those features it gives you an answer, it’s a bicycle, it’s a truck or it’s a motor cycle.
- So with deep learning, one of our solutions is to take a very large unlabeled data set and we put that into a training model using artificial neural networks and then that goes into the neural network itself, when we create a neural network, we train the neural network, we put the bicycle in and then it comes back and says if its a truck it comes back and says well you need to change that to bicycle and then it changes all those weights going backward they call it back propagation and let it know it’s a bicycle and that’s how it learns.
- Once you have trained the neural network, you then put the new data in and they call this testing the model so you need to have some data you’ve kept off to the side where you know the answer to and you take that and you provide the required output and you say is this neural network working correctly, did it identify a bike as a bike, truck as a truck, a motor cycle as a motor cycle.
- In this we are going to see how these fit together in a minute, the system is able to make predictions or take decisions based on past data, that’s very important for machine learning is that we are looking at stuff and based on what’s been there before, we are creating a decision(we are coloring a beach ball, predicting weather in chicago).
PROS OF MACHINE LEARNING:
- What is nice about Machine Learning is a very powerful processing capacity it gives quick and accurate outcomes so you get results right away.
- Once you program the system, the results are very fast and the decisions and predictions are better, they are more accurate, they are consistent, you can analyze very large amounts of data, some of these data things that they are analyzing now are petabytes and terabytes of data, it would take hundreds of people, hundreds of years to go through some of this data do the same thing that the machine learning can do in a very short period of time.
- Its in expensive compared to hiring hundreds of people so because a very affordable way to move into the future is to apply the machine learning to whatever businesses you are working on.
- In deep learning systems think and learn like humans using artificial neural networks again it’s like a magic box.
- Performance improves with more data.
- Scalability : You can scale it up, you can scale it down, you can increase what you are looking at current.
- Problem solved in an end-to-end method – So instead of having to break it apart and you have the first piece coming in and you identify tires and the second piece is identifying, labeling handle bars and then you bring that together that if it has handle bars, and tires it as a bicycle and if it has something that looks like a large square is probably a trick the neural networks does this all in one network.
- Best feature are selected by the system.
- It is a subset of Machine learning.
- Lesser testing time.
Artificial Intelligence Vs Machine Learning Vs Deep Learning
Deep Learning which is a subset of machine learning which is a subset of Artificial Intelligence.
Artificial Intelligence:- Intelligent machines which think and act like human beings.
Machine Learning:- Systems learn things without being performed to do so.
Deep Learning:- Machine think like human brains using artificial neural networks.
Real Life examples
- News generation.
- Amazon echo
- Google command
- Tons of smart home devices.
- Spam Detection.
- Search engine result refining.
- Exit sign.
- Chat Bots.
Types Of Machine Learning
- Supervised Learning.
- Unsupervised Learning.
- Reinforcement Learning.
- Systems are able to predict future outcomes based on past data.
- Requires Both an input and output to be given to the model for it to be trained.
- Systems are able to identify hidden patterns from the input data provided.
- By making the data more readable and organize the patterns, similarities or anomalies become more evident.
- Systems are given no training.
- It learns on the basis of the reward/ punishment it received for performing its last action.
- It helps increase the efficiency of a tool/ function or a program.
Machine learning and deep learning
Machine learning Deep Learning
Enables machine to take decisions Enables machines to take decisions with
on their own, based on past data. the help of artificial neural network.
Needs only a small amount of training Needs a large amount of training data.
Works well on low end systems. Needs high end system to work.
Most features need to be identified in The machines learns the features
advance and manually coded. from the data it is provided.
The problem is divided into parts and The problem is solved in an end
solved individually and then combined. to end manner.
Testing takes longer time. Testing takes less time.
Crisp rule explain why a certain Since the system takes decisions based
decision was taken. on it's own logic, the reasoning may be difficult to interpret.
A GLIMPSE INTO THE FUTURE
- Detecting crimes before they happen.
- Humanoid AI helpers.
- Increased efficiency in health care.
- Better marketing techniques.
- Increased Personalization.
- Hyper intelligent personal assistants.
For more on machine learning :-https://wrytin.com/trishakarmakar/machine-learning-jv19a95t