Tuesday, 13 December 2022

AI vs. Machine Learning vs. Deep Learning | Machine Learning Training with Python

AI vs Machine Learning vs Deep Learning

Hello, everyone, This is Mohit and welcome to today's topic of discussion on AI vs. Machine Learning vs. Deep Learning. 

These are the terms that confuse many people, and if you, too, are among them, let me resolve it for you.      

So let's move on and understand how exactly they differ from each other. So let's start with artificial intelligence. The term artificial intelligence was first coined in the year 1956. The concept is pretty old, but it has gained its popularity recently. But why well, the reason is earlier we had a minimal amount of data the data we had Was not enough to predict the accurate result. Still, a tremendous increase in the number of data statistics suggests that by 2020 the accumulated volume of data will increase from 4.

Now, we have more advanced algorithms and high-end computing power and storage that can deal with such large amounts of data as a result.

Just for your understanding of what does AI well, it's nothing but a technique that enables the MachineMachine to act like humans by replicating the behavior and nature with AI. 
The MachineMachine can learn from the experience. The machines are just responses based on new input, thereby performing human-like tasks. 

Artificial intelligence can be trained to accomplish specific tasks by processing large amounts of data and recognizing patterns in them. You can consider that building an artificial intelligence is like Building a Church, and the first church took generations to finish. 

So most of the workers were working in it never saw the outcome those working on it took pride in their craft building bricks and chiseling stone that was going to be placed into the magnificent structure. 

So as AI researchers, we should think of ourselves as humble brick makers whose job is to study how to build components example Parts is planners or learning algorithms accept anything that someday.

Someone and somewhere will integrate into the intelligent systems some of the examples of artificial intelligence from our day-to-day life.
Our Apple series is just playing computer Tesla self-driving cars, and many more these examples are based on deep learning and natural language processing.

Well, this was about what is and how it gains its hype—so moving on ahead. Let's discuss machine learning and see what it is and the white pros of an introduction. Well, Machine learning came into existence in the late 80sand the early 90s, but what were the issues with the people which made the machine learning come into existence? 

Let us discuss them one by one in the field of Statistics. 

The problem was how to efficiently train large complex models in computer science and artificial intelligence. The problem was how to prepare a more robust version of the AI system, while in the case of Neuroscience problem faced by the researchers was how to design the operation model of the brain. 

 Now this Machine learning shifted its focus from the symbolic approaches. 

It had inherited from the AI and move towards the methods and model. It had borrowed from statistics and probability theory. So let's proceed and see what exactly is machine learning. Well, Machine learning is a subset of AI which The computer to act and make data-driven decisions to carry out a specific task. 

These programs are algorithms that are designed in a way that they can learn and improve over time when exposed to new data. Let's see an example of machine learning. Let's say you want to create a system that tells the expected weight of a person based on its side. 

The first thing you do is collect the data. 

Let's see there is how your data looks like now. Each point on the graph represents one data point to start. We can draw a simple line to predict the weight based on height. For example, a simple line W equal x minus hundred where W is waiting for kgs and edges hide and centimeter this line can help us to make the prediction. 

Our main goal is to reduce the difference between the estimated value and the actual value. So to achieve it, we try to draw a straight line that fits all these different points and minimize the error. 

So our primary goal is to minimize the error and make them as small as possible, decreasing the error or the difference between the actual value and estimated value. I increase the performance of the model further on the more data points. We collect the better. 

Our model will become we can also improve our model by adding more variables and creating different production lines for them once the line is created. So from the next time we feed new data, for example, the height of a person to the model, it would easily predict the data for you, and it will tell you what has predicted weight could be. 

I hope you got a clear understanding of machine learning. I am so moving on ahead. 

Let's learn about deep learning. Now, what is deep learning? 

You can consider a deep learning model as a rocket engine, and its fuel its vast amount of data that we feed to these algorithms the concept of deep learning is not new. Still, recently it's hype as increase and deep learning are getting more attention. 

This field is a particular kind of machine learning that is inspired by the functionality of our brain cells called neurons, which led to the concept of artificial neural networks. 

It merely takes the data connection between all the artificial neurons and adjusts them according to the data pattern. More neurons are added at the size of the data is largest automatically features learning at multiple levels of abstraction. 

You are thereby allowing a system to learn complex function mapping without depending on any specific algorithm. You know, no one knows what happens inside a neural network and why it works so well, so currently, you can call it as a black box. Let us discuss some of the examples of deep learning and understand it in a better way. 

Let me start with a simple example and explain to you how things happen at a conceptual level. Let us try and understand how you recognize a square from other shapes. The first thing you do is check whether there are four lines associated with a figure or not a simple concept, right? 

If yes, we further check if they are connected and closed again for a few years. 

We finally check whether it is perpendicular, and all its sides are equal, correct if Fulfills. Yes, it is a square. It is nothing but a nested hierarchy of Concepts that we did here we took a complex task of identifying a square and this case and broken into more straightforward tasks. 

Now this deep learning also does the same thing, but at a larger scale, let's take an example of MachineMachine, which recognizes the animal. The task of the MachineMachine is to know whether the given image is of a cat or a dog. 

What if we were asked to resolve the same issue using the concept of MachineMachine learning what we would do first. 

We would Define the features such as check whether the animal has whiskers are not a check if the animal has pointed ears or not or whether its tail is straight or curved in short. 

We will Define the facial features and let the system identify which features are more critical in classifying a particular animal now; when it comes to deep learning takes this to one step ahead of deep learning.
Automatically, it finds out the function most important for classification compared to machine learning, where we Had to give out those features by now manually. 

I guess you have understood that AI is a more significant picture and machine learning and deep learning, or it's apart. So let's move on and focus our discussion on machine learning and deep learning the easiest way to understand the difference between the MachineMachine learning and deep learning is to know that deep learning is machine learning more explicitly. 

It is the next evolution of machine learning. 

Let's take a few critical parameters and compare Machine learning with deep learning. 

So starting with data dependencies, the most crucial difference between deep learning and machine learning is its performance as the volume of the data gets increased from the below graph. 

You can see that when the size of the data is a small deep learning algorithm doesn't perform that well, but why well?  

 Is because a deep learning algorithm needs a large amount of data to understand it correctly. On the other hand, the machine learning algorithm can efficiently work with smaller data set fine. 

Next comes the hardware dependencies deep learning. Are heavily dependent on high-end machines while the machine learning algorithm can work on low and devices as well.  

Because the requirement of deep learning algorithm includes GPUs, which is an integral part of its working, the Deep learning algorithm requires GPUs as they do a large amount of matrix multiplication operations. These operations can only be efficiently optimized using a GPU as it is built for this purpose. 

Only our third parameter will be feature engineering will feature engineering is a process of putting the domain knowledge to reduce the complexity of the data and make patterns more visible to learning algorithms. 

This process is difficult and expensive in terms of time and expertise in the case of machine learning. 

For example, the features can be a pixel value shaping texture position orientation or anything fine. The performance of most of the machine learning algorithms depends on how accurately the elements are identified and extracted. In contrast, in the case of deep learning algorithms, it tries to learn high-level features from the data. 

It is a distinctive part of deep learning, which makes it way ahead of traditional machine learning deep learning reduces the task of developing a new feature.

Extractor for every problem like in the case of CN n algorithm first tries to learn the low-level features of the image such as edges and lines. Then it proceeds to the parts of faces of people and then finally to the high-level representation of the face. 

I hope that things are getting more apparent to you. 

So let's move on ahead and see the next parameter. So our following setting problem-solving approach when we are solving a problem using traditional machine learning algorithms. It is generally recommended that we first breakdown the problem into different sub-parts, address them individually, and then finally combine them to get the desired result. 

 It is how the machine I learning algorithm handles.

On the other hand, the Deep learning algorithm solves the problem from end to end. Let's take an example to understand this suppose. You have a task of multiple object detection. 

And your task is to identify. 

What is the object, and where itis present in the image? 

So, let's see and compare. How will you tackle this issue using the concept of machine learning and deep learning, starting with machine learning in a typical machine learning approach? 

You would divide the problem into two steps first object detection and then object recognization. 

First of all, you would use a bounding box detection algorithm like grab cut, for example, to scan through the image and find out all the possible objects. 

Now, once the objects are recognized, you would use the object recognization algorithms like SVM with hog to identify relevant objects. 

Now, finally, when you combine the result, you would be able to identify. What is the object and where it is present in the image? On the other hand, in an in-depth learning approach, you would process the process from end to end, for example, in a euro net, a type of deep learning algorithm. 

You would pass an image, and it would give out the location along with the name of the object. Now, let's move on to our fifth comparison parameter, its execution time.
Usually, a deep learning algorithm takes a long time to train because there's so many parameter ina deep learning algorithm that makes the training longer than usual the training might even last for two weeks or more than that. 

If you are training entirely from scratch, whereas in the case of machine learning, it relatively takes much less time to prepare, ranging from a few weeks to few Arts. 

Now, the execution time is completely reversed when it comes to the testing of data during testing the Deep learning algorithm takes much less time to run. 

Whereas if you compare it with a KNN algorithm, which is a type of machine learning algorithm, the test time increases as the size of the data increase last but not the least.

We have interpretability as a factor for comparison of machine learning, and Running this fact is the main reason why deep learning is still thought ten times before anyone uses it in the industry. 

Let's take an example, suppose. 

We use deep learning to give automated scoring two essays the performance it provides, and scoring is quite excellent and is near to the human achievement, but there's an issue with it. 

It does not reveal white has given that score indeed mathematically. It is possible to find out which node of a deep neural network was activated, but we don't know what the neurons are supposed to model and what these layers of neuron we're doing collectively. 

So if able to interpret the result, on the other hand, a machine learning algorithm, like a decision tree, gives USA crisp rule for void chose and watered chose. 

So it is particularly easy to interpret the reasoning behind; therefore, the algorithms like a decision tree and linear or logistic regression are primarily used in the industry for interpretability before we end this session. 

Let me summarize things for you. Machine learning uses algorithms to parse the data to learn from the data and make an informed decision based on what it has learned fine.

Now this deep learning structure algorithms in layers to create an artificial neural network that can learn and make Intelligent Decisions.

On their own finally, deep learning is a subfield of machine learning. At the same time, both fall under the broad category of artificial intelligence. Deep learning is behind the most human-like artificial intelligence. 

No comments:

Post a Comment