Original article was published by Mussaveer shariff on Artificial Intelligence on Medium
Machine learning And Deep learning…
In recent years the terms Machine learning and the Deep learning are getting popular among the many organizations…
lets get some knowledge about them…
Basically 5 qualities will make the human being intelligent:
- Estimating the values or simply predicting something.
- Classifying the objects whatever we see.
- Grouping — Similar to classification.
- Recommending something to others based on their experience on that specific area.
- Making decisions wisely.
So, trying to imply all the above qualities into the machine by manually(artificially) simply known as Artificial intelligence.
- Machine learning
- Deep learning and Neural networks
They are the parts of artificial intelligence….
Machine learning — An approach to achieve Artificial Intelligence
“Field of study that gives computers the ability to learn without being explicitly programmed” — Arthur Samuel
It is the practice of using some algorithms to break up data, and learn from the data. And then use this learning to predict some things…We are not using any hard coding to training the algorithm .It gets trained on the data on its own…but by applying some science to data we can change the format of the data in order to get algorithm/model easily trained on that…
Training the model on the huge amount of data makes the model to predict accurately and perform some specific tasks…
Always remember that more the data more the accuracy we get…
Here we have some specific types of learning such as,
- Supervised learning.
- Unsupervised learning.
- Reinforcement learning.
The two main tasks of the supervised learning are Classification and Regression
Simply classifies to which category it belongs to (yes or no, 1 or 0).
Regression-Predicting the continuous value
Estimating the relationships between the dependent variables and the independent variables and predicting according to that.
In Supervised learning we can find solutions for problems like..
How much money will we make by spending more dollars on digital advertising? Will this loan applicant pay back the loan or not? What’s going to happen to the stock market tomorrow? etc.
In supervised learning problems, we start with a data set containing training examples with associated correct labels. For example, when learning to classify handwritten digits, a supervised learning algorithm takes thousands of pictures of handwritten digits along with labels containing the correct number each image represents. The algorithm will then learn the relationship between the images and their associated numbers, and apply that learned relationship to classify completely new images (without labels) that the machine hasn’t seen before.
Here the process is clustering and the dimensionality reduction.
The task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups
“It is not the daily increase, but the daily decrease. Hack away at the unessential.” — Bruce Lee
Dimensionality reduction looks a lot like compression. This is about trying to reduce the complexity of the data while keeping as much of the relevant structure as possible.
How do you find the underlying structure of a dataset? How do you summarize it and group it most usefully? How do you effectively represent data in a compressed format? These are the goals of unsupervised learning, which is called “unsupervised” because you start with unlabeled data (there’s no Y).
The two unsupervised learning tasks we will explore are clustering the data into groups by similarity and reducing dimensionality to compress the data while maintaining its structure and usefulness.