what is Machine learning?

what is Machine learning?

it's method of data analysis which automates analytical model building.

Using algorithms that iteratively learn from data.

Machine learning allows computer to find hidden insights without being explicitly programmed where to look.

So the Machine Learning algorithm on it's own will figure it out, what patterns and what features are important.

Applications:

1. Text sentiments analysis
2. Email spam filtering
3. and more

Supervised learning:

Supervised learning algorithms are trained using labeled examples. For example: Where then input and the desired output are known.

• Text of an email being labeled as spam vs legitimate.
• Movie reviews being labeled as positive or negative

The learning algorithm receives a set of inputs along with the corresponding correct outputs.

The algorithms is going to learn by comparing it's actual output with the correct outputs in order to find an error and then it's going to modify it's internal parameters accordingly to achieve the best results on it's own, without you explicitly programming.

Supervised learning is commonly used application where historical data points predict likely future events. For example, Information of previous emails you've received that someone has labeled as spam or legitimate. This historical data can be used to create a spam filter for future emails.

Text classification and recognition this is really common and widely applicable use of ml

Supervised Machine Learning Process:

1. Data Acquisition
2. acquire data from some source
3. Data Cleaning
4. convert raw text into numerical vectors that ml model can understand
5. Data Split: once the data is formatted and cleaned
6. you split it on
7. Training Set i.e Fitting the model
8. train your ml model
9. commonly about 70% of the total data
10. Test Set
11. Evaluate model performance on data model has never seen before
12. 30% of our data
13. Model Testing:
14. We take the model we trained on and we test it, then we evaluate how well the model performed.
15. using different evaluation metrics
16. Model Evaluation:
17. After testing we can either decide to improve the model by editing some parameters, essentially repeat the process until we're satisfied with our model performance
18. Deployment of Model