Sam’s Machine Learning
What is Machine Learning? Internet definition:
Machine learning is a subset of AI, which uses algorithms that learn from data to make predictions. These predictions can be generated through supervised learning, where algorithms learn patterns from existing data, or unsupervised learning, where they discover general patterns in data.
The Current World View of Machine Learning:
Searching the internet for Learning Algorithms and Model principles, we found the Images #1 and Table #1 presenting the components of Learning Algorithms. However, we do not believe these Machine Learning approaches would work with real world diverse and complicated data. Therefore, we will not spend any energy on these approaches and we will be presenting our intelligent, dynamic and flexible Machine learning processes.
Our View of Data as Historical, Current and Future:
When viewing data as "historical, current, and future," it means considering data not just as a snapshot of the present moment. It is also a collection of past information that can support current decisions and potential predictions about what might happen in the future. It is essentially using the past to understand the present and anticipate future trends or outcomes.
Our Approach to Machine Learning:
How to teach a computer to look for Donold Duck in these two bags of toys?
Our Zeros and Ones Concept and Components
The basic concept of any computer is the binary bit (0,1). Computer Science was able to turn this binary Zeros and Ones into a revolution of technologies that we use today. With the same thinking, we use the concept of Zeros and Ones to build search patterns. We would also use Dynamic Business Rules as guidance in building the search patterns. We build from Zeros and Ones a Byte, then use bytes to build a word and use words to build patterns. The best way to make our concept clearer is by presenting the Donald Duck toy as an example.
The following images are the Bits (Zeros and Ones) which would be used to build one Byte for Donald where we turn the Byte into Patterns:
Donald Duck has very distinct features which are the hat, the beak, the eyes, and the red bowtie. These Donald Duck features are the Zeros and Ones we would be using in our pattern building. We can put together a combinations of Donald Duck’s distinct features and come up with many numbers of possible patterns as shown in image #4.
Once we have these patterns, we do not stop, we would use of the speed of the computer and take each pattern to create any number of possible scales and colors which could exist. For example, we can rotate the pattern sideways, upside-down, right, left, mirror image, … etc. as shown in image #5.
Now we would have any number of possible images which could represent Donald Duck. By having all possible patterns of Donald Duck, the computer can go back and start searching the two bags of toys and try to find any toy which would resemble Donald Duck.
In a nutshell, we empowered the computer to have the ability to learn from the Zeros and Ones of any object. As for data and business logics, we can use Machine Learning to enable the computer to use Zeros and Ones to find patterns and use patterns to look for endless number of possibilities.
Our Machine Learning, Data, System and Intelligence:
We believe that our Machine Learning approaches, methodologies and Business Rules can perform the job of data and system analysts. We would be able to make our Machine Learning think like humans. The key is that a data and system analyst’s tasks are to examine (search, analyze, compare, find patterns, …) data, Big Data, system processes and business processes. With these processes, they would be able to help with the decision-making. With Big Data and all possible search, analysis, mining and all the known data processing, it would be impossible for a human to perform such tasks with speed and accuracy. This is besides the needed efforts for cross-referencing of these processed data and patterns would take in terms of time and money.
As for making our Machine Learning intelligent, we would be picking the brain, approaches, thinking and educated guessing of data and system analysts. We also would be getting the gurus and the experts thinking processes and approaches. We would be using these human abilities to emulate human intelligence. Plus, the speed of the computer processes and abilities of running endless possibilities, the parsing of historical data and patterns would give our Machine Learning a big boost in intelligence.
Our Machine Learning View:
Our Machine Learning (ML) View is that ML would perform the jobs of many data and system analysts. In short, our ML is an independent intelligent data and system Powerhouse. Our ML’s jobs or tasks would include all the possible data handling as follows:
1. Working with large data sets
2. Collecting
3. Searching
4. Parsing
5. Analysis
6. Extracting
7. Cleaning and pruning
8. Sorting
9. Updating
10. Conversion
11. Formatting – Integration
12. Customization
13. Cross-referencing-Intersecting
14. Report making
15. Graphing
Recommended by LinkedIn
16. Virtualization
17. Modeling
18. Correlation
19. Relationship
20. Mining
21. Pattern recognition
22. Personalization
23. Habits
24. Prediction
25. Tendencies
26. Mapping
27. Decision-making support
28. Audit trailing
29. Tracking
30. History tracking
31. Trend recognition
32. Validation
33. Certification
34. Maintaining
35. Managing
36. Testing
37. Securing
38. Compression-Encryption
39. Documentation
40. Storing
41. Other Misc.
We can state with confidence that no human can perform all the listed processes or steps mentioned above, but our Machine Learning would be able to perform all the tasks with astonishing speed and accuracy.
How to architect-design Our Machine Learning?
Our Approach to Machine Learning:
1. Turning Data into Long Integers for faster processing
2. Our Machine Learning Data Structure using Data Matrices
3. Engines
4. Management system
5. Storage. (how to store data and engines for fast creating, running, loading and communicating)
6. Dynamic Business Rules
7. Virtual Testing
8. Libraries of Patterns
9. Lessons Learned
We would be more than happy to present our ML’s architect-design.
Thanks,
Sam Eldin
(847) 606.9999
Great explanation!