Studying Machine Learning and Deep Learning from Scratch

I was interested in learning machine learning and deep learning ever since I realized its potential to apply to many research problems in power systems research. So I started learning it. So far, I have done one Coursera specialization, a course (you can probably guess this) and I'm currently doing another specialization. Before this, I went through several youtube videos to get a feel for what ML really is.

Apart from this, I'm enrolled in the program by Dr. Michal Fabinger @Tokyo Data Science

My goal here is to recommend the flow of this process, which would have been very helpful in the beginning for me. Although I have given Coursera links most of the content is available open-source for free. So here it goes,

Search youtube for videos that explain what machine learning is. There are a lot out there. Don't get stuck in this just take one hour that should be enough. TensorFlow ML Zero to Hero
Then start learning. A good place to start is Coursera - AMII specialization
The next one I would recommend is Machine Learning - Andrew Ng which covers the theory behind machine learning. Also, this one is a must-do in the world of machine learning
Then I would recommend Deep Learning - deeplearning.ai which covers deep learning (I did not do this and started doing the next one. I'll let you know how that goes)
Then finally I would recommend Advanced Machine Learning - HSE

Also, there are several others I have planned to do in the coming months which are on ML tools.

That's it for now. I'm sure there are others that are good resources but here I'm giving you my own path. Feel free to comment with your own suggestions.

Comments

How to program in R language in Jupyter Notebooks using Conda environments

In this blog post, we will discuss how to use conda environments to install the R kernel and program in R in Jupyter notebooks. 1. Install conda The first step in using conda environments is to install conda itself. You can download the conda installer from the Anaconda website and follow the instructions to install it on your system. Once you have conda installed, you can create and manage virtual environments. 2. Create a new conda environment To create a new conda environment, you can use the following command in your terminal: conda create -n myrenv This will create a new environment called "myenv" that you can use to manage your packages and dependencies. You can activate this environment by using the following command: conda activate myrenv 3. Install the R kernel Now that you have an active conda environment, you can use it to install the R kernel. You can do this by using the following command (you may have to press Enter key several times to finish the process): c...

Webinar Series on Smart Grid and Microgrids by Smart Grid Research Lab, University of Moratuwa

This webinar series is created by the Smart Grid Research Lab of the University of Moratuwa , Sri Lanka. As a research assistant and a Ph.D. student, I had the honor of organizing the series. The webinar series is titled "Discussion forum on Smart Grid and Microgrids". It will cover the fundamentals of Smart Grid and Microgrids and the research areas of Smart Grid Research Lab. The webinars will be uploaded to YouTube and created as a playlist . Check out the introduction to the webinar series and the lab by Prof. K. T. M. U. Hemapala.

Cracking the Black Box: Six Lenses for Understanding Deep Learning

Deep learning has revolutionised technology, giving us everything from uncannily smart chatbots to medical imaging that can spot diseases better than the human eye. Yet, for a long time, a central mystery has haunted the field: why do these enormous models work so well? According to classical statistics, a model with billions of parameters—far more than its training data—should fail spectacularly. It ought to memorise the data, noise and all, and be unable to generalise to new, unseen examples. But deep neural networks defy this wisdom. They generalise brilliantly. How do we explain this apparent magic? There isn't one single answer. Instead, researchers view the problem through several different theoretical "lenses." Here are six of the most important ones. 1. The Linearisation Lens: The Neural Tangent Kernel (NTK) ⚙️ The NTK offers a startling insight: what if, under the right conditions, a massively complex neural network is just a simple, linear model in disguise? The...

Kalhan's Blog

Search This Blog