Machine Learning

1.what is definition of Machine Learning?

The first thing I would like to share with you is the definition of machine learning. Simply put, it is a branch of artificial intelligence that teaches the machine how to adapt to the problems it faces, whether mathematical and computational problems or many other things, such as predicting specific information through the use of the machine, and here is the concept of intelligence.

In terms of adaptation, it is achieved. As for the second term, which is artificial, it is achieved in machines that achieve this adaptation, and here the word "machine" does not mean that it is only a laptop or a computer. I cannot say about cars, industrial machines, and mathematical machines, and also

Robots and others are all considered machines. Simply put, we can summarize the concept of machine learning as a technology that we can use to provide and improve machines in problem solving through experience and expertise by teaching models a certain experience that they gain to predict each other with different information to obtain knowledge and reach a decision.

2. What are the types of Machine Learning?

There are four types of Machine Learning. two of them are commonly used in the tech field, while the other two are least commonly used.

1. Supervised Learning: It's a type of Machine Learning, in which it has a specific and known output of sample called "label". The sample "label" includes:

A. Classification Problem: it's a type of problem in which the prediction output is either discrete or quantitate data, the idea behind this problem is to classify the data into categories.

B. Regression Problem: it's a type of problem in which the prediction output is a continuous numerical data.

2. Unsupervised Learning: it doesn't have known output of sample, for example: clustering.

The samples are usually unlabeled.

The difference between clustering and classification is that clustering can be used to classify the data into categories, yet the data are unknown, on the other hand, the classification contains known data.

The other two types of Machine Learning

Unlike the supervised and unsupervised learning, they're not commonly used.

3. Semi Supervised Learning:

These algorithms combine between known data and

unknown ones.

It aims to predict the unknown data as well as known ones, for instance: the Machine Translation.

4. Reinforcement Learning:

These algorithms react according to the surrounding environment and it aims to achieve a specific task that involves several steps, for instance: Reports that make a specific task.

3.what is the difference between Overfitting & Underfitting?

1.Overfitting: it's when the model learns the training, for example: "too well" or its performance is "100%". This model can't predict any new data. Because it has learnt the specific patterns, and can't understand any other data.

2. Good fit model: it's when the model familiarizes itself with the training, for example: "not too well" The models should be of this type

3. Under fitting: it's when the model is simple and failed in the training, for example: its performance is less than "65%".

4.How can you create Model of Machine Learning?

The number of phases is different depending on the data.

1. Data collection: this is the first phase to create a model, in this phase you must collect your data from various sources and display it.

2. Data cleaning: this is the second phase, in this phase

A. you can encode the data.

B. you can remove the null values or you can fill them.

C. The idea behind data cleaning is that you attempt to balance your data so that you avoid the inductive Bias.

These processes aren't necessary to implement them all.

The implementation of these processes comes down to the requirements of the data.

3. Feature selection: in this phase you must select the most important features which the target depends on them and have an effect on them.

4. Data splitting: in this phase you can divide data into two parts: (Features) which are called X and (Target) which is called Y.

5. Data training: in this phase you select a specific model such as "Decision Tree", in this case (Classification) or "Logistic Regression", in this case, regression model learns and gain more knowledge

6. Prediction or testing phase: This phase a model must predict data.

this phase a model must predict data.

for arbic:

1.?? ?? ????? ?????? ??????

??? ??? ??? ??????? ??? ?? ????? ?????? ?????. ??????? ?? ??? ?? ???? ?????? ????????? ???? ???? ????? ????? ?????? ?? ??????? ???? ???????? ???? ???? ????? ?????? ??????? ?? ????? ???? ?????? ??? ?????? ???????? ????? ?? ???? ??????? ?????? ???? ??????? ?? ??????.

?? ??? ??????? ??? ?? ??????. ??? ??????? ?????? ??? ????????? ?????? ?? ?????? ???? ???? ??? ??????? ???? ?? ???? ???? "???" ??? ???? ????? ????? ?? ???????. ?? ?????? ?? ???? ?? ????????? ??????? ????????? ??????? ????????? ?????.????????? ?????? ???? ????? ????. ?????? ?????? ????? ????? ?????? ????? ?????? ?????? ????????? ?????? ?????? ?????? ?? ?? ???????? ?? ???? ??????? ??????? ?? ???? ????? ??????? ???? ????? ??????? ?????? ?????? ????? ???????? ?????? ?????? ??? ??????? ? ???????????????.

2. ?? ?? ????? ?????? ??????

???? ????? ????? ?? ?????? ?????. ????? ???? ???? ????????? ?? ???? ???????????? ????? ??????? ??????? ????? ?????????.

1. ?????? ?????? ???????: ?? ??? ?? ?????? ?????? ??? ???? ?? ?????? ????? ??????? ?? ?????? ???? "???????". ????? ???? "???????" ?? ???:

?. ????? ???????: ?? ??? ?? ??????? ???? ???? ???? ?????? ?????? ??? ?????? ?????? ?? ?????? ????? ??????? ???? ??? ??????? ?? ????? ???????? ??? ????.

?. ????? ????????: ?? ??? ?? ??????? ???? ???? ???? ???? ?????? ????? ?? ?????? ????? ??????.

2. ?????? ??? ?????? ???????: ?? ????? ??? ?????? ?????? ??????? ??? ???? ??????: ???????.

???? ?? ???? ??????? ??? ??????.

????? ??? ??????? ???????? ?? ??? ???? ??????? ??????? ?????? ???????? ??? ????? ???? ???????? ??? ??????? ?? ????? ????? ????? ??????? ?????????????????.

??????? ??????? ?? ?????? ?????

??? ??? ?????? ?????? ??????? ???? ?????? ???????? ?? ??? ?????????? ???? ????.

3. ?????? ??? ?????? ???????:

???? ??? ??????????? ??? ???????? ???????? ?

??????.

????? ??? ?????? ????????? ??? ???????? ????? ????????? ??? ???? ??????: ??????? ??????.

4. ?????? ??????:

?????? ??? ??????????? ?? ?????? ??????? ????? ??? ????? ???? ????? ????? ??? ?????? ??? ???? ??????: ???????? ???? ????????????????.

3.?? ?? ????? ??? ??????? ?????? ???????? ???????

1.???????: ????? ????? ????? ??????? ???????? ??? ???? ??????: "??? ????" ?? ?? ???? ????? "100%". ?? ?????? ??? ??????? ?????? ??? ?????? ?????. ???? ???? ??????? ?????? ??? ????? ??? ?? ?????? ????.

2. ??????? ????? ???????: ????? ????? ??????? ??? ???????? ??? ???? ??????: "??? ?????" ??? ?? ???? ??????? ?? ??? ?????

3. ??? ???????: ????? ???? ??????? ?????? ??????? ?? ???????? ??? ???? ??????: ?????????????"65%".

4. ??? ????? ????? ????? ?????? ??????

????? ??? ??????? ??? ????????.

1. ??? ????????: ??? ?? ??????? ?????? ?????? ???????? ?? ??? ??????? ??? ???? ??? ??????? ?? ????? ?????? ??????.

2. ????? ????????: ???? ?? ??????? ??????? ?? ??? ???????

?. ????? ????? ????????.

?. ????? ????? ????? ??????? ?? ????? ?????.

?. ?????? ???? ????? ???????? ?? ?????? ?????? ??????? ???? ????? ?????? ??????????.

??? ???????? ???? ?????? ???????? ??????.

????? ????? ??? ???????? ??? ????????????????.

3. ?????? ???????: ?? ??? ??????? ??? ????? ??? ??????? ???? ????? ????? ????? ????? ??? ????? ?????.

4. ????? ????????: ?? ??? ??????? ????? ????? ???????? ??? ?????: (???????) ????? ????? X ? (?????) ????? Y.

5. ??????? ??? ????????: ?? ??? ??????? ??? ????? ????? ???? ??? "???? ??????" ?? ??? ?????? (???????) ?? "???????? ????????"? ?? ??? ?????? ????? ????? ???????? ?????? ?????? ?? ???????

6. ????? ?????? ?? ????????: ??? ??????? ??? ?? ????? ??????? ?????????.

?? ??? ??????? ??? ?? ????? ?????????????????.