How Does DEEP LEARNING actually Works ?

GUPTA, Gagan       Posted by GUPTA, Gagan
      Published: July 9, 2021

Enjoy listening to this Blog while you are working with something else !


Deep learning is a subset of machine learning where neural networks - algorithms inspired by the human brain - learn from large amounts of data. Deep learning algorithms perform a task repeatedly and gradually improve the outcome through deep layers that enable progressive learning. It's part of a broader family of machine learning methods based on neural networks. The "deep" in deep learning refers to the use of multiple layers in the network through which the data is transformed.

Over the last half-dozen years, deep learning, a branch of artificial intelligence inspired by the structure of the human brain, has made enormous strides in giving machines the ability to intuit the physical world. The most powerful tech companies in the world have been quietly deploying deep learning to improve their products and services, and none has invested more than Google. A few years ago, a Google deep learning network was shown 10 million unlabeled images from YouTube, and proved to be nearly twice as accurate at identifying the objects in the images (cats, human faces, flowers, various species of fish, and thousands of others) as any previous method. When Google deployed deep learning on its Android voice search, errors dropped by 25% overnight.

Historically, computers performed tasks by being programmed with deterministic algorithms, which detailed every step that had to be taken. This worked well in many situations, from performing elaborate calculations to defeating chess grandmasters. But it hasn't worked as well in situations where providing an explicit algorithm wasn't possible-such as recognizing faces or emotions,

Deep learning systems are modeled after the neural networks in the neocortex of the human brain, where higher-level cognition occurs. In the brain, a neuron is a cell that transmits electrical or chemical information. When connected with other neurons, it forms a neural network. In machines, the neurons are virtual-basically bits of code running statistical regressions. String enough of these virtual neurons together and you get a virtual neural network. Think of every neuron in the network below as a simple statistical model: it takes in some inputs, and it passes along some output.

Deep neural networks are not a simple stack of neural layers. Indeed, to solve more and more complex problems, it is not enough to add more and more layers. The two major problems of neural networks, which are the learning difficulty and the increasing computational complexity with the number of layers, are indeed always present. The solutions provided by recent research make it possible to limit these problems but not to solve them completely. In practice, there are different types of deep neural networks that aim to solve different problems.

Deep learning allows artificial intelligence systems to imitate the manner in which humans acquire certain kinds of knowledge. DL algorithms try to draw conclusions - similar to how humans do it - by continually analyzing data. To achieve this, DL uses artificial neural networks (ANNs).

Our On-Premise Corporate Classroom Training is designed for your immediate training needs

How Does DEEP LEARNING actually Works ?
How Does DEEP LEARNING actually Works ?

How does deep learning work?

In simpler terms, DL's learning process takes place by modifying the system actions based on a continuous feedback loop. The learning system is rewarded for every right action and punished for the wrong ones. The system tries to adjust its actions to maximize the reward.

Deep learning uses supervised, semi-supervised, as well as unsupervised learning models to train.

Deep learning is made possible by artificial neural networks. They're built by drawing inspiration from the neural networks of the human brain. A massive number of perceptrons - the artificial counterpart of neurons - are stacked together to form ANNs.

While traditional neural networks contain two to three hidden layers, deep networks can have even 150 layers.

An easy way of understanding how deep learning works is by looking at convolutional neural networks (CNNs). It's one of the most popular types of deep neural networks other than recurrent neural networks (RNNs), generative adversarial networks (GANs), and feedforward neural networks.

CNN extracts features directly from the images, eliminating the need for manual feature extraction. None of the features are pre-trained; instead, they are learned by the network when it trains on the given set of images. This automated feature extraction characteristic makes deep learning models highly effective for object classification and other computer vision applications.

The reason why deep neural networks are highly accurate in identifying features and classifying images is due to the hundreds of layers they hold. Each layer would learn to identify specific features, and as the number of layers increases, the complexity of the learned image features increases.

For instance, you have pictures of cats and dogs, thousands of them. You need to make to piles. You can train an ANN to recognize the animal.

How does it do it? With math. For instance, and to simplify, let's say that there are only 3 parameters that identify the animal: x, y, and z. we will try to get an equation in the form:

w1 X + w2 Y + w3 Z = animal

The goal is to learn the combination of weights w1, w2, w3 that classify the animals with probability close to 1

The classified data may look like this:

2.4 w1 + 0.443 w2 + 1.09 w3 = cat

And you would need lots of this in order to calculate the right weights.

so, when you do not know what the animal is, you multiply the parameters by the corresponding weights and the result would be either a cat or dog.

Our On-Premise Corporate Classroom Training is designed for your immediate training needs

How to Choose Between Machine Learning and Deep Learning

Machine learning offers a variety of techniques and models you can choose based on your application, the size of data you're processing, and the type of problem you want to solve. A successful deep learning application requires a very large amount of data (thousands of images) to train the model, as well as GPUs, or graphics processing units, to rapidly process your data.

When choosing between machine learning and deep learning, consider whether you have a high-performance GPU and lots of labeled data. If you don't have either of those things, it may make more sense to use machine learning instead of deep learning. Deep learning is generally more complex, so you'll need at least a few thousand images to get reliable results. Having a high-performance GPU means the model will take less time to analyze all those images.

The Future of Deep Learning

New technologies and algorithms are being developed constantly to help computers get more sophisticated. It may be in the future that deep learning changes the way computer memory works, giving us more vast storage options than we ever imagined. Enhanced customer experience, more specific marketing techniques, and more convenience are all part of the future of AI. With these may also come deeper discussions on privacy issues-currently companies can get huge amounts of information about consumers in an instant, and discussions are always happening about privacy and security of information. Deep learning may be able to help enhance cybersecurity, and new regulations will likely have to be enacted about privacy and buying and selling data. All of these areas are likely to be part of the exciting future of deep learning.


- Deep Learning uses a Neural Network to imitate animal intelligence.
- There are three types of layers of neurons in a neural network: the Input Layer, the Hidden Layer's, and the Output Layer.
- Connections between neurons are associated with a weight, dictating the importance of the input value.
- Neurons apply an Activation Function on the data to 'standardize' the output coming out of the neuron.
- To train a Neural Network, you need a large data set.
- Iterating through the data set and comparing the outputs will produce a Cost Function, indicating how much the AI is off from the real outputs.
- After every iteration through the data set, the weights between neurons are adjusted using Gradient Descent to reduce the cost function.
- Training a deep learning model can take a long time, from days to weeks.
- To solve more and more complex problems, it is not enough to add more and more layers.

Support our effort by subscribing to our youtube channel. Update yourself with our latest videos on Data Science.

Looking forward to see you soon, till then Keep Learning !

Our On-Premise Corporate Classroom Training is designed for your immediate training needs

How Does DEEP LEARNING actually Works ?

Corporate Scholarship Career Courses