We know this term must have created the vision of difficult terms along with long sequence of codes following and what not.
Also we know for most of us given a choice, no one would really like to go for machine languages.
To make it profound let’s ask a question to ourselves if presented with an option to choose between programming and machine languages what you would like to choose.
Unless and until you a hard-core programmer and coding is your favourite past time you would like to choose programming languages just for the fact that they are easy to use and are presented with a certain format and standard library functions.
But that’s the only reason we are here. We are not here to lead you to a path we are just trying to let you see the different aspects of the road you are not choosing.
We will begin with the advantages of machine language.
- The foremost advantage is that machine level languages present the idea of a generic machine to the programmer.
- It is easier and much less costly to write and debug programs for a given task
Machine languages are likely to be more reliable and “obviously correct”
- It is easier to understand and maintain programs in a machine language
- It is a most efficient in term of storage area use and execution speed and it also allows programmer to utilize the computer’s potential for processing data.
- Machine Language is the only language that is directly understood by the computer. It does not need any translator program.
Done with the advantages we present you with variety of resources that could be used to learn these languages.
There are obviously a number of ways to go about learning machine learning
Machine Learning Books
There are a lot of machine learning books but choosing best amongst them and one that will suit you to begin with might be a tough job so here we have sorted some books for you to start with.
There are a few books out there that encourage eager programmers to get started by teaching the minimum intuition for an algorithm and point to tools and libraries so that you can run off to and try things out.
Programming Collective Intelligence: Building Smart Web 2.0 Applications: This book was written for your reference with little on theory, heavy on code examples and practical web problems and solutions. Skim it & get set go with the exercises.
Machine Learning for Hackers : It again provides worked examples that are practical, but it has a more of a data analysis flavour and uses R.
Data Mining: Practical Machine Learning Tools and Techniques, Third Edition : This book is basically designed to try things out, implement my own algorithms as plug-ins and generally practice Machine Learning and the broader process of Data Mining.
Machine Learning: This is a basic staged book and does include formulas and lots of references. It’s a text book but is also very accessible with grounded motivations for each algorithm.
Learn from data: This book provides a perfect introduction to machine learning & prepares you to understand complex areas of machine learning. This book has provided ‘to the point’ explanations instead of lengthy and go-around explanations.
After recommending the books we will recommend some overview paper you might use it as reference as paper is like a snippet of a textbook, but describes an experiment or some other frontier of the field.
The Discipline of Machine Learning: This was a piece of the argument Mitchell used to convince the President of CMU to create a standalone Machine Learning department for a subject that will still be around in 100 years
A Few Useful Things to Know about Machine Learning: This is a great paper because it pulls back from specific algorithms and motivates a number of important issues such as feature selection generalizability and model simplicity.
The best MOOCs on machine learning today
Beginner Machine Learning:
1. Machine Learning (Stanford): This highly-rated Stanford course is perhaps the best introduction to machine learning. They are known for their ability to expertly explain the mathematical concepts involved in different areas of machine learning.
2. Principles of Autonomy and Decision Making: This course basically deals with the implementation of logic & from logic to heuristics to model-based reasoning.
Intermediate Machine Learning:
3. Machine Learning (University of Washington): This interactive course goes beyond basic concepts to explore neural networks, learning theory and vector machines — among other things. “Supervised learning” — meaning that the correct answers is usually given to the student during class is provided as an additional beneficiary.
4. Introduction to Convex Optimization: This high-level course will help students recognize and tackle convex optimization problems & also go over applications in areas like finance, computational geometry, mechanical engineering and more.
Advanced Machine Learning:
5. Machine Learning (MIT): This graduate level course from MIT approaches machine learning through the lens of statistical inference.
6. Topics in Statistics: This course provides an in-depth analysis of the theories behind statistical learning, and covers empirical process theory.
7. Neural Networks for Machine Learning: This course introduces users to algorithms that are “inspired by the way the human brain works.”
These algorithms are used to build machines with things like speech recognition, image retrieval, and personalized recommendations for users.
Video is another popular way to get started in machine learning.
With the advent of sites like YouTube and videoLectures.net the learning has been made relatively easier and you can watch a lot of machine learning videos two of them we have recommended over.
Stanford Machine Learning: Available via Coursera and taught by Andrew Ng. In addition to enrolling, you can watch all the lectures anytime and get the hand-outs and lecture notes from the actual Stanford CS229 course.
The course includes homework and quizzes and focuses on linear algebra and using Octave.
Caltech Learning from Data: Available via edX and taught by Yaser Abu-Mostafa. All the lectures and materials are available on the Caltech.
You can take it at your own pace and complete the homework and assignments. It covers similar subjects and goes into a little bit more details and is more mathematical. The homework is probably too challenging for a beginner.