Did you ever wondered how google translates an entire web page to a different language in a matter of seconds on your phone gallery groups images based on their location all of this is a product of deep learning.
But what exactly is deep learning??
Deep learning is a subset of machine learning which in turn is a subset of artificial learning intelligence
see more - what is artificial intelligence
Artificial intelligence is a technique that enable a machine to mimic human behavior. Machine learning is a technique to achieve AI through algorithms trained with data and finally deep learning is a type of machine learning inspired by the structure of the human brain in terms of deep learning this structure is called an artificial neural network.
Lets understand deep learning better and how its different from machine learning.
Say we create a machine that could differentiate between tomatoes and cherries .If done using machine learning we’d have to tell the machine the feature based on which the two can be differentiated these features could be the size and the type of stem on them.With deep learning on the other hand the feature are picked out by the neural network without human intervention of course that king of independence comes at the cost of having a much higher volume of data to train our machine .
Now lets dive into the working of the neural networks .
Here we have three students ,Each of them write down the digit nine on a piece of paper notably they don’t all write it identically the human brain easily recognize the digits but what is a computer had to recognize them that’s where deep learning comes in.
Here’s is a neural network trained to identify handwritten digits each number is present as an image of 28 times 28 pixels now that amounts to a total of 784 pixels neurons .The core entity of a neural network is where the information processing takes place each of the 784 pixels is fed to a neuron in the first layer of our neural network. This forms the input layer on the other end .We have the output layer with each neuron representing a digit with the hidden layer existing between them .The information is transfer from one layer to another layer over connecting channels. Each of these has a value attached to it and hence is called a weighted channel.
All neurons have a unique number associated with it called bias. This bias is added to the weighted sum of inputs reaching the neuron, which is then applied to a function known as the activation function. The result of the activation function determines, if the neuron get activated .Every activated neuron passes on information to the following layers
This continues up till the second last layer .The one neuron activated in the output layer corresponds to the input digit .The weight and bias are continuously adjusted to produce a well trained network .
So where is deep learning applied in customer support :
When most converse with customer support agents the conversation seems so real, they don’t even realize that actually a bot on the other side
In medical care neural networks detect cancer cells and analyze MRI images to give detailed results .
Self driving cars what seem like science fiction is now a reality .Apple ,Tesla and Nissan are only a few of the companies working on self driving cars.
So deep learning has a vast scope but it too faces some limitations :
The first as we discussed earlier is data, While deep learning is the most efficient way to deal with unstructured data.A neural network requires a massive volume of data to train ,lets assume we always have access to the necessary amount of data processing this is not within the capability of every machine and that brings us to our second limitation.
Computational power, Training and neural networks requires graphical processing units which have thousands of course as compared to CPU's and GPU's are of course more expensive.
So here a short quiz for you arrange the following statements in order to describe the working of a neural network ;
finally we come down to training time. Deep neural networks take hours or even months to train .The time increases with the amount of data and number of layers in the network .
- The bias is added
- The weighted sum of the inputs is calculated
- Specific neuron is activated
- The result is fed to an activation function
Leave your answer in comments section below three of you stand a chance to win amazon vouchers so hurry up.
Some of the popular deep learning frameworks include ,Tensorflow high torch cars. Deep learning forge a cafe and Microsoft cognitive toolkit. Considering the future prediction of the deep learning and AI we seem to have only scratched the surface .In fact horse technology is working on a device for blind that uses deep learning with computer vision to describe the world to the user ,replicating the human mind at the entirety may be not just an episode of science fiction of too long. The future is indeed full of surprises. That is deep learning for you in short
If you enjoyed this blog do like and share it and don't forget to answer the quiz above in comment section.
THANK YOU FOR YOUR SUPPORT AND CARE
No comments:
Post a Comment