Machine Learning analyses the given input and it predicts the possible outcome of it without any programming code.
For a model to make predictions in a robust way, it needs to be fed with data. The more the merrier. Fortunately, the web today is full of data sources. On many occasions, the data is collected by private companies for their own benefit, but there are also other initiatives, such as, for example, open data portals.
When all the particular cases have been observed, the induction is considered complete, so the generalization it gives rise to is considered valid. However, in most cases it is impossible to obtain a complete induction, so the statement to which it gives rise is subject to a certain degree of uncertainty, and consequently cannot be considered as a formally valid inference scheme nor can it be considered. can justify empirically.
On many occasions the field of action of Machine Learning overlaps with that of Data Mining Since the two disciplines are focused on data analysis, however, Machine Learning focuses more on the study of the computational complexity of problems with the intention of making them feasible from a practical point of view, not just a theoretical one.
Once we have the data, we are ready to begin the learning process. This process, carried out by an algorithm, tries to analyze and explore the data in search of hidden patterns. The result of this learning, sometimes, is nothing more than a function that operates on the data to calculate a certain prediction. There are so many technologies prevailing in addition to this.
How Machine Learning Can Be Used?
We are experiencing a real explosion with a wide variety of offerings related to Machine Learning. A few years ago it was a field reserved for research centres creators and owners of powerful algorithms inaccessible to those who could not be an expert in the field.
On the other hand, projects created and maintained by the community have emerged that make applications and libraries available to the general public that allow anyone less profane in the field to access this type of algorithm in their own applications and public showing more interest towards these apps and Gadgets.
In addition, due to the very demanding requirements of the infrastructure on which this type of application must run, large cloud hosting companies, such as Microsoft with Azure Machine Learning and Amazon with Machine Learning, have arranged of services for the execution and use of in our Machine Learning applications:
And finally, to complete the offer, all the large companies are already providing any user with the possibility of accessing open projects, where algorithms, documentation and examples are provided for access to algorithms:
- Microsoft with Oxford.
- Google with Tensor Flow.
- Facebook with FAIR.
You can not use all these algorithms without any training, but without being an expert in Mathematics or Statistics, you can now access online training that will provide us with the basic knowledge necessary to start working with these algorithms and open the door to Machine Learning.
