Hey, everyone, today I’ll take you through a very interesting topic that is none other than deep learning.
Instead of you doing all your work, you have a machine to finish it for you, or it can do something which you thought was not possible. For instance, predicting the future, like predicting earthquake, tsunami so that preventive measures can be taken to save lives. Chabot’s virtual personal assistants like Siri and iPhones Google assistant. And believe me, it is getting smarter day by day with deep learning self-driving cars. It will be a blessing for elderly people and disabled people who find it difficult to drive on their own.
And on top of that, it can also avoid a lot of accidents that happen due to human error. Google Eye Doctor. So this is a recent initiative by Google where Google is working with an Indian Icare chain to develop an A.I. software which can examine retina scans to identify a condition called diabetic retinopathy, which can cause blindness and music composer who thought that we can have an A.I. music composer using deep learning and maybe in the coming years, even machines will start winning Grammys.
And one of my favorites, a dream reading machine, what so many unrealistic applications of and deep learning that we have seen so far. I was wondering that whether we can capture dreams in the form of a video or something, and I wasn’t surprised to find out that this was tried in Japan a few years back on three test subjects, and they were able to achieve close to 60 percent accuracy. And that is amazing. But I’m not sure that whether people would want to be a test subject for this or not because it can reveal all your dreams
So this sets the base for you. And we are ready to understand what is artificial intelligence. Artificial intelligence is nothing but the capability of a machine to imitate.
Intelligent human behavior is achieved by mimicking a human brain, by understanding how it things, how it learns and work while trying to solve a problem. For example, a machine playing chess or a voice activated software which helps you with various things in your phone, or a numberplate recognition system which captures the numberplate often over speeding car and processes to extract the registration number and identify the owner of the car so that he can be charged. And all this was very easy to implement before deep learning.
Now let’s understand the various subsets of artificial intelligence. So till now, you’d have heard a lot about artificial intelligence, machine learning and deep learning. However, do you know the relationship between all three of them? It’s a deep learning is a Suffield of a soft field of artificial intelligence. So it is a soft field of machine learning, which is a soft field of artificial intelligence. So when we look at something like Alpha Go, it is often portrayed as a big success for deep learning.
But it’s actually a combination of ideas from several different areas of AI and machine learning, like deep learning, reinforcement learning, self play, etc.. And the idea behind deep neural networks is not new, but it dates back to 1950s. However, it became possible to practically implemented only when we had the new high end resource capability. So I hope that you have understood what is artificial intelligence. So let’s explore machine learning followed by its limitations. Some machine learning is a subset of artificial intelligence which provide computers with the ability to learn without being explicitly programmed in machine learning.
We do not have to define all the steps or conditions like any other programming application. However, we have to train the machine on a training data set large enough to create a model which helps the machine to take decisions based on its learning. For example, if we have to determine the species of a flower using machine, then first we need to train the machine using a flower dataset which contains various characteristics of different flowers along with the respective species.
As you can see here in the image, we have got several separate Petland battle with and the species of the flower too. So using this input data said the machine will create a model which can be used to classify a flower. Next will pass on a set of characteristics as input to the model, and it will output the name of the flower. And this process of training a machine to create a model and use it for decision making is called machine learning.
However, this process had some limitations. Machine learning is not capable of handling high dimensional data. That is where input and output is large and it is present in multiple dimensions and handling and processing such a data becomes very complex. And resource exhausted, and this is termed as the curse of dimensionality. So to understand this in simpler terms, let us consider a line of hundred yards. And let us assume that you dropped a coin somewhere in the line.
You’ll easily find the coin by simply walking on the line, a line in a single dimension entity. Now, let’s consider that you have got a square of side hundred yards each and you dropped a coin somewhere inside the square. Now definitely will take more time to find the coin within that square. A square is a two dimensional entity. Now let’s take it a step ahead and consider a cube of side hundred yards each and you drop the coin somewhere inside the cube.
Now it is even more difficult to find the coin. So if we see that the complexities increasing as the dimensions are increasing and in real life, the high dimensional data that we are talking about has got many dimensions, which makes it very, very complex to handle and process.
The high dimensional data can be easily found in use cases like image processing, natural language processing, image translation, etc. and machine learning was not capable of solving this use cases and hence deep learning came to the rescue.
So deep learning is capable of handling the high dimensional data and is also efficient in focusing on the right features on its own. And this process is called feature extraction. Now let’s try and understand how deep learning works. So in an attempt to reimagine a human brain, deep learning studies, the basic unit of a brain called a brain cell or a neuron inspired from a neuron, an artificial neuron or a Perceptron was developed. [06:42]
So if we focus on the structure of a biological neuron, it has got dendrites and these are used to receive inputs. And these inputs are summed up inside the cell body and using the axon, it is passed on to the next biological neuron. So similarly, a Perceptron receives multiple inputs, applies various transformations and functions, and provides an output, as we know that our brain consists of multiple connected neurons called neural network. We can also have a network of artificial neurons called Perceptron to form a deep neural network.
Let’s understand how deep neural network looks like. So any deep neural network will consist of three types of layers, the input layer, the hidden layer and the output layer. So if you see in the diagram, the first layer is the input layer, which receives all the inputs. The last layer is the output layer, which gives the desired output and all the layers in between. These layers are called hidden layers and there can be any number of hidden layers thanks to the high end resources available these days and the number of hidden layers and the number of Perceptron in each year will be entirely dependent on the use case that you’re trying to solve.
And there is mechanisms to decide. The number of hidden layers, however, will not get into that in this session. Now, since you have a picture of deep neural network, let’s try to get a high level view of how deep neural network solves a problem. For example, we want to perform image recognition using deep networks. So we’ll have to pass this high dimensional data to the input layer and to match the dimensionality of the input data. The input layer will contain multiple sub layers of Perceptron so that it can consume the entire input and the output received from the input layer will contain patterns and will only be able to identify the edges and images based on the contrast levels.
And this output will be fed to hidden layer one, where it will be able to identify various facial features like eyes, nose, years, etc.. Now this will be fed to hidden layer tool where it will be able to form the entire faces and send to the output layer to be classified and given a name. Now think if any of this layers is missing or the neural network is not deep enough, then what will happen simple will not be able to accurately identify the images.
And this is the very reason why these use cases did not have a solution all these years prior to deep learning. So just to take this further will try to apply deep network on an endless dataset. So the endless dataset consists of sixty thousand training samples and ten thousand testing samples of handwritten digit images. And the task here is to train a model which can accurately identify the desired present on the image. And to solve this use case, a deep network will be created with multiple hidden layers to process all the sixty thousand images pixel by pixel and finally will receive an output.
So the output will be an array of index 029 where each index corresponds to the respective digit. So index zero contains the probability of zero being the digit present on the input image.