This blog post will help Getting start to Machine Learning Journey to Deep Learning . I have tried to keep it short and clean .
Machine learning is a method of data analysis that automates analytical model building. Using algorithms that iteratively learn from data, machine learning allows computers to find hidden insights without being explicitly programmed where to look. Essentially, it is a method of teaching computers to make and improve predictions based on some data.
In the past decade, machine learning has given us self-driving cars, practical speech recognition, effective web search, and a vastly improved understanding of the human genome. Machine learning is so pervasive today that you probably use it dozens of times a day without knowing it. Many researchers also think it is the best way to make progress towards human-level AI. Machine learning is a subset of AI. The theory is simple, machines take data and ‘learn’ for themselves.
Artificial intelligence is a state of machine when it can take decisions just like a human.In today’s modern world a machine fully capable to take decisions just like human brain even in the most complex and difficult environment can be said to have achieved Artificial Intelligence. It is not necessary for the machine to have arms and shape of a human. A simple computer box can also be artificially intelligent.
Today tiny fragments of AI are all around us. Siri is AI, Alexa is AI, automatic turning off of the light based in number of people inside the room is AI. But the full and final state of AI would be reached when the human mind can be implemented or emulated completely. That emulated human mind computer would behave exactly like human and may be even more efficient. It would provide exactly same responses.
Absolute Beginner :
If you start with hardest stuff first,It will be way easier to get discouraged and give up so create small achievable goals during the learning process to stay motivated .
~ Before we start learning or deep dive into ML : ~
“Python is a Good Choice” scientific and numeric computing (with the help of libraries such as NumPy, SciPy, etc.), Support’s wide range of Libraries for various algorithms and have large community in ML .
2. Basics Maths Knowledge about Algebra,Calculus,Probability & Statistics: (Optional: This is not must, Having some basic knowledge about it would be good, Since we can take the advantage of Python Scientific libraries like Numpy & Scipy ,because while learning different algorithms you need to make visualization about the data & use it’s properties in algorithm’s using algebra,calculus concept’s)
3. Learn Python Libraries: : There are tons of machine learning libraries already written for Python. Just Learn it one by one .
OpenCV : Helpful Analyzing Images/Videos and Applying Cascade’s and More etc,
Numpy : Helpful performing Mathematical operations
Matplotlib: Helps in Plotting Mathematically operations Visually in Dimensions
Pandas : Helps in Gathering,Preparing the Data to feed into our Algorithms.
After Learning above 3 Powerful Libraries . Jump right into .
4. Andrew-Ng Course : There is a Excellent and Highly Recommended Free Course by Andrew Ng at coursera, course is a very good starting point for you to get your understanding about algorithms in Theory and different concept’s to Machine Learning .
After Finishing Andrew-Ng Course, Grabbing Lot of Theoretical Knowledge about Algorithms .
5. Learn Scikit-Learn Library : (one of the most powerful API with different Algorithms,Powerful Data Encoders etc)
~ Now it’s time to Apply Theoretical Knowledge into Practical ~
6. I Would Highly Suggest you to read Python Machine Learning Edition 2 by Sebastian Raschka
From theory(Mathematical explanations) of different machine learning algorithms & optimization methods to practical code , covers large varieties of Practical Algorithms with Python, aswell as Using it with Scikit-Learn API, replaying it with Tensorflow API .
7. CheatSheet !!!!!!!!
Essential Cheat Sheets for Machine Learning and Deep Learning Engineers_Learning machine learning and deep learning is difficult for newbies. As well as deep learning libraries are difficult…_startupsventurecapital.com
8. Develop CNN(Convolution Neural Network) to identify Dogs VS Cats Using TensorFlow
9. Simulating Self Driving Car with Keras :
10. Neural Network Applied Series on GTA-5 :
This is a big, big journey. Very tiring, very irritating and exceptionally time consuming. If you can make your way through this list, by the end you should at least be familiar with the field of machine learning, and be prepared to figure out what you want to learn next. Good luck!
~Let’s Spread this AI Power ! ~
Note : Whatever i have shared totally based on the thing’s i have tried out during the learning process .
~Feedback’s and Edit’s are Welcome ~