WHAT IS CNN IN DEEP LEARNING

 WHAT IS CNN IN DEEP LEARNING

Over the past few decades, Deep Learning has proved to be a very powerful tool because of its ability to handle large amounts of data. The interest in using hidden layers has transcended traditional techniques, particularly in pattern recognition. One of the most popular deep neural networks is the convolutional neural network.

CNN Deep Learning

Since the 1950s, in the early days of AI, researchers have struggled to create a system that can understand visual data. In later years, this field became known as computer vision. In 2012, computer vision took a big leap when a group of researchers from the University of Toronto developed an AI model that surpassed the best image recognition algorithms by a huge margin.

The AI ​​system, which became known as AlexNet (named after its main creator, Alex Krzyzewski), won the 2012 ImageNet Computer Vision Contest with 85 percent accuracy. The runner-up scored a modest 74 percent in the test.

At the heart of AlexNet was a special kind of neural network that roughly simulates human vision. Over the years CNN has become a very important part of many computer vision applications and hence a part of any computer vision course online. So let's take a look at the workings of CNN.

HISTORY OF CNN

CNN was first developed and used around the 1980s. The most that a CNN could do at the time was to recognize handwritten digits. It was mostly used in postal areas to read zip codes, pin codes, etc. The important thing to remember about any deep learning model is that it requires a huge amount of data to train and also requires a lot of computing resources. This was a major drawback for CNN at that time and hence CNN was limited to postal sectors only and it failed to enter the world of machine learning.

In 2012 Alex Krzyzewski realized that it was time to bring back the branch of deep learning that used multi-layered neural networks. The availability of larger sets of data, having more specialized ImageNet datasets with millions of labeled images, and an abundance of computing resources enabled the researchers to regenerate CNNs.

UNDERSTAND CNN

In deep learning, convolutional neural networks (CNN/ConvNet) are a class of deep neural networks that are commonly applied to analyze visual imagery. Now when we think of a neural network we think of matrix multiplication but this is not the case with ConvNet. It uses a special technique called convolution. Now in mathematics, convolution is a mathematical operation on two functions that produces a third function that expresses how the shape of one is modified by the other.

But we don't really need to go past the math part to understand what a CNN is or how it works.

The bottom line is that the role of ConvNet is to reduce the image to a form that is easy to process without losing important features to obtain a good prediction.

WORKING OF CNN

Convolutional neural networks are made up of multiple layers of artificial neurons. Artificial neurons, a rough copy of their biological counterparts, are mathematical functions that calculate the weighted sum of multiple inputs and output an activation value. When you input an image into a ConvNet, each layer generates a number of activation functions that are passed on to the next layer.

The first layer usually extracts basic features such as horizontal or diagonal edges. This output is passed to the next layer which detects more complex features such as corners or combining edges. As we go deeper into the network, it can identify even more complex features like objects, faces, etc.

UNDERSTAND POOLING LAYER

Similar to the convolutional layer, the pooling layer is responsible for reducing the spatial size of the convolutional feature. This is to reduce the computational power required to process the data by reducing the dimensions. There are two types of pooling average pooling and maximum pooling.

LIMIT IN CNN

Despite the power and resource complexity of CNNs, they provide profound results. At the core of all this, it is simply recognizing patterns and details that are so subtle and imperceptible that it goes unnoticed by the human eye. But it fails when it comes to understanding the content of an image.