If you’ve spent quite enough time on the internet, it’s pretty likely that you’ve heard something related to Artificial Intelligence or Machine Learning. In fact, Machine Learning is a part of Artificial Intelligence. So let’s dive into how to get started in Machine Learning.
What is Machine Learning?
Machine Learning is the field of study that gives computers the ability to learn without being explicitly programmedArthur Samuel
When we do traditional computer programming, we tell the computer what to do & when to do. This is not the case with Machine Learning (or ML in short). In ML, it’s the computer that decides by itself how to solve a particular problem.
How to get started in Machine Learning?
Although Machine Learning is not a new concept, it’s very clear that it had an enormous boost in the recent years. So more and more people are interested in learning ML.
There is a resonating name that comes to any ML student’s mind when talking about Machine Learning. He is Prof. Andrew Ng, who is a professor at the Stanford University Department of Computer Science and Department of Electrical Engineering.
Prof. Ng has a great introductory course on Machine Learning, on the Coursera website. Here’s the link to the course, https://www.coursera.org/learn/machine-learning.
more on the Course
This is an 11-week course which is FREE. Wooh! wait a minute before you think that’s too long. Machine Learning is a vast subject. By the end of this course according to Prof. Ng’s words, you will be an expert in Machine Learning.
I’ve personally taken & completed the course. It’s really satisfying once you complete such an important course. You don’t have to know Calculus or have extensive knowledge of Mathematics either.
I’m sure almost all the students who’ve taken the course would agree to one of Prof. Ng’s catchphrases, “it’s alright if you don’t understand it totally right now. Just keep going”.
What’s covered in the Course?
How about almost all the things you need to become an expert in Machine Learning? These are Prof. Ng’s words.
- Introduction to ML
- Supervised & Unsupervised Learning
- Model & Cost function
- Gradient descent (for linear regression)
- Linear algebra review including Matrices & Vectors (BONUS)
- Multivariate linear regression
- Gradient descent (for multiple variables)
- Features & Polynomial regression
- Normal equation
- Octave/ Matlab assignments
- Classification & Representation
- Decision boundary
- Logistic regression model
- Multiclass classification
- Solving the problem of Overfitting
- Neural networks
- Unrolling parameters
- Gradient checking
- Random initialization
- Evaluating a Learning algorithm
- Bias vs Variance
- Learning curves
- Handling skewed data
- Using large datasets
- Large margin classification
- Support vector machines (SVMs)
- K-Means algorithm
- Dimensionality reduction
- Principal component analysis (PCA)
- Density estimation
- Anomaly detection
- Multivariate Gaussian distribution
- Gradient descent (for large datasets)
Please consider these points are not in any special order, but rather I’ve put them here so that you can get an idea of what’s covered in this course.
What will I be able to do after following this course?
You can pretty much improve much further to do any ML task with the basic knowledge gained from this course. Furthermore, during this course also there are assignments & activities including,
- Building an anomaly detection system
- A photo OCR application
- A spam email classifier
Alright, so that’s it. That’s how to get started in Machine Learning. I think I’ve convinced you enough to follow this great course. If you apply for financial aid, you can also get a certificate for a reduced price or FREE (given that you would have to wait 2 weeks for the approval). You can even share that certificate on LinkedIn.