Image from freepik https://www.freepik.com/free-photos-vectors/people

Machine Learning Plan And Resources

Machine Learning is taking the world away by its popularity and applications. If you also want to dive into the fascinating world of machine learning and don’t know where to start from, you’re at the right place.

Note: While learning from these videos, do take a note and a pen and write down all the new stuff you learn because there’s gonna be a lot of new jargon to fill up your mind with. And I advise to use a pen and paper over digital notes as it helps in retaining the memory better.

Day 1

On your first day of learning Machine Learning, you have to get a basic understanding of what ML is and what it consists of. Now understanding ML can be a hectic job but I just got the right article for you.

With this article, you’ll have a good knowledge of what ML is and what are its types. You’ll also get to know what are the different methods or models we use in ML to train the algorithms. Click the link below.

Get your basic understanding of Machine Learning here.

Also watch this awesome video below from Google

Day 2

Now that you’re familiar with what Machine Learning is and what we do and can do with this fascinating wonder it’s time to dive a bit deep.

On the second day, You will have to look at the different categories of ML. Now ML is surely a wide and broad topic, but some great intellectuals managed to narrow this learning into Three different categories.

You can learn about the categories of ML from the following link:-

You ca also try watching this video: Click here

Day 3

After knowing the categories of ML and understanding the basic differences between each of them, we have to learn about Supervised Learning in ML in order to classify the problem we have at hand.

To know about the Supervised Learning and get comfortable with it, watch this video:-

Day 4

After getting to know about supervised learning and be able to distinguish supervised learning problem, now we have to look at unsupervised learning.

In the following video you will get to know all about there is to Unsupervised Learning and you will be able to distinguish Unsupervised Learning problems than the other two.

Day 5

Last but not the least, after understanding about Supervised and Unsupervised Learning, we’re gonna have to have a understanding of Reinforcement Learning.

This type of ML type is a bit different from the other two types but it is equally as important.

In the following video, you’ll get a good grasp of what Reinforcement Learning is.

Day 6

Well, by now you’ll have a good knowledge of what ML is and how to identify an ML problem and of course! How to solve them by putting them into the three different categories you have learned in the previous days.

Now if you dive deeper in ML you’ll see that there are a few problems that we intend to eradicate or solve with the help of Machine Learning algorithms, obviously.

Click the link below to have a look at these problems.

https://www.practicalai.io/categorizing-machine-learning-problems/

Day 7

The most famous ML problem is the Regression problem and the regression analysis we do in order to understand and try to solve the basic problems that fall into this paradigm. So on this day, you’ll learn about the Regression problem and the types of Regression.

Regression can be of two types: Linear Regression and Multiple Regression

Click the link to know all about Regression:-

http://ufldl.stanford.edu/tutorial/supervised/LinearRegression/

Also, watch this video:-

https://youtu.be/ZkjP5RJLQF4

Day 8

The second most popular problem in ML that comes after Regression is the famous Classification problem.

In statistics, classification is the problem of identifying to which of a set of categories a new observation belongs, on the basis of a training set of data containing observations whose category membership is known.

To know deeply about Classification in ML, watch the following video:-

Day 9

The third most popular and the last problem of Machine Learning that we’re gonna learn here is the Clustering Problem.

Cluster analysis or clustering is the task of grouping a set of objects in such a way that objects in the same group (called a cluster) are more similar (in some sense) to each other than to those in other groups (clusters). It is a main task of exploratory data mining, and a common technique for statistical data analysis, used in many fields, including pattern recognitionimage analysisinformation retrievalbioinformaticsdata compressioncomputer graphics and machine learning.

For better understanding, watch this video:-

Day 10

It’s day 10 and we’ve come a long way but the journey isn’t over yet. I’m sure by now you must have acquired great and deep knowledge of Machine Learning and all the problems associated with it.

Now let’s take a look at the kinds of Machine Learning. A machine learning algorithm can be classified as either parametric or non-parametric.

Watch this video to know better:-

Day 11

I think it’s time now to know about the various tools used in the process of Machine Learning. It’s an ocean of tools which we use to ease the whole machine learning process but let’s take a view at the most useful ones.

Here’s a very good Medium article to give you the knowledge of some of the most popular and useful Machine Learning tools.

https://medium.com/@shivashishdf.thakur/top-15-most-used-machine-learning-tools-by-experts-d6602f1ac14c

Also, watch this video:-

Day 12

Now that you’ve got all the tools at the back of your head, Let’s talk about the most useful and probably the most important tool we’re gonna use while experimenting with Machine Learning.

Tensorflow is An end-to-end open source machine learning platform for everyone. Discover TensorFlow’s flexible ecosystem of tools, libraries and community resources.

Have a look at this link to know all about tensorflow:-

https://medium.com/@erikhallstrm/hello-world-tensorflow-649b15aed18c

Also, watch this video:-

Day 13

After getting tensorflow hands-on, it’s time to move on two the second most useful and popular Machine Learning tool which is Scikit-Learn.

Scikit-learn (formerly scikits.learn and also known as sklearn) is a free software machine learning library for the Python programming language.[3] It features various classificationregression and clustering algorithms including support vector machinesrandom forestsgradient boostingk-means and DBSCAN, and is designed to interoperate with the Python numerical and scientific libraries NumPy and SciPy.

Have a look at this article for understanding Scikit-Learn through tutorials:-

https://scikit-learn.org/stable/tutorial/index.html

You can also watch this video to better understand:-

Day 14

After these two tools, we’re gonna move on to the last Machine Learning tool we’re gonna learn about which is also the third most popular and useful Machine Learning tool that is used in the industry… Pytorch.

PyTorch is an open source machine learning library based on the Torch library, used for applications such as computer vision and natural language processing, primarily developed by Facebook’s AI Research lab. It is free and open-source software released under the Modified BSD license.

Have a look at this article to have a better understanding of Pytorch:-

http://blog.gaurav.im/2017/04/24/a-gentle-intro-to-pytorch/

Also, watch this video to get Pytorch in a much better way:-

Day 15

Now that we’ve got comfortable with some of the useful Machine Learning tools, I want you to get back to algorithms. Since Machine Learning is all about algorithms and how you manipulate these algorithms to train your Machine Learning models and get the expected results.

We have already talked about Linear Regression which is probably the most used algorithm in Machine Learning but since it’s obvious that we’re not gonna use only one algorithm so it’s compulsory that we learn about some more important ones.

Logistic Regression. It is used to estimate discrete values (usually binary values like 0/1) from a set of independent variables. It helps predict the probability of an event by fitting data to a logit function. It is also called logit regression.

Look at this article for more info:-

https://towardsdatascience.com/logistic-regression-detailed-overview-46c4da4303bc

Day 16

After getting comfortable with Logistic Regression, let’s have a look at Decision Tree algorithm.

It is one of the most popular machine learning algorithms in use today; this is a supervised learning algorithm that is used for classifying problems. It works well classifying for both categorical and continuous dependent variables. In this algorithm, we split the population into two or more homogeneous sets based on the most significant attributes/ independent variables.

Have a look at this article for more info:-

https://medium.com/greyatom/decision-trees-a-simple-way-to-visualize-a-decision-dc506a403aeb

Also, watch this video if the article didn’t work for you:-

Day 17

After understanding the Decision Tree Algorithm, we will take a look at Naive Bayes algorithm.

A Naive Bayes classifier assumes that the presence of a particular feature in a class is unrelated to the presence of any other feature. Even if these features are related to each other, a Naive Bayes classifier would consider all of these properties independently when calculating the probability of a particular outcome.

Have a look at this article for more info:-

Also, watch this video on Naive Bayes algorithm:-

Day 18

On this day, we are going to take a look at another algorithm called KNN (K- Nearest Neighbors) and is arguably one of the most important Machine Learning algorithm.

This algorithm can be applied to both classification and regression problems. Apparently, within the Data Science industry, it’s more widely used to solve classification problems. It’s a simple algorithm that stores all available cases and classifies any new cases by taking a majority vote of its k neighbors. The case is then assigned to the class with which it has the most in common. A distance function performs this measurement.

Take a look at this article to have a better understanding of KNN:-

Also, have a look at this video to better understand KNN algorithm:-

Day 19

On this day, we’re going to have a look at K-Means algorithm.

It is an unsupervised algorithm that solves clustering problems. Data sets are classified into a particular number of clusters (let’s call that number K) in such a way that all the data points within a cluster are homogeneous and heterogeneous from the data in other clusters.

Take a look at this article to better understand:-

https://towardsdatascience.com/k-means-clustering-algorithm-applications-evaluation-methods-and-drawbacks-aa03e644b48a

Also, watch this video:-

Day 20

On our 20th day, we are going to take a look at our last algorithm called as Random Forest algorithm.

A collective of decision trees is called a Random Forest. To classify a new object based on its attributes, each tree is classified, and the tree “votes” for that class. The forest chooses the classification having the most votes (over all the trees in the forest).

Here’s an article for you to understand Random Forest algorithm:-

https://medium.com/@Synced/how-random-forest-algorithm-works-in-machine-learning-3c0fe15b6674

Also, look at this video:-

Day 21

It’s day 21 and we sure have come a long way, and I’m sure now you’re equipped with some deep and broad knowledge of Machine Learning and beyond. But when we talk about machine learning, we do so in the terms of Deep Learning. And our journey of Machine Learning isn’t really complete if we don’t get to know about Deep Learning.

Have a look at this article to know about Deep Learning:-

http://nikhilbuduma.com/2014/12/29/deep-learning-in-a-nutshell/

Also, look at this introductory video on Deep Learning:-

Day 22

After having a light knowledge of Deep Learning, we have to dive deeper because deep learning is somehow connected to Neural Networks which is very important concept in the world of Machine Learning.

Let’s talk about Linear Factor Models.

Take a look at this article:-

https://web.stanford.edu/~wfsharpe/mia/fac/mia_fac2.htm

Have a look at this video too:-

Day 23

From this day onwards, we will be learning about Neural Networks and how it’s connected with Deep Learning.

neural network is a network or circuit of neurons, or in a modern sense, an artificial neural network, composed of artificial neurons or nodes. Thus a neural network is either a biological neural network, made up of real biological neurons, or an artificial neural network, for solving artificial intelligence (AI) problems.

Have a look at this article:-

http://news.mit.edu/2017/explained-neural-networks-deep-learning-0414

Also this video will help you understand Neural Network better:-

Day 24

Now we’re going to take a look at the 6 types of Neural Networks which are currently used in Machine Learning.

These are parts of Artificial Neural Network but in Machine Learning they’re used in the same place of Neural Networks.

Today, we will talk about Feedforward Neural Network – Artificial Neuron.

Have a look at this article:-

https://en.wikipedia.org/wiki/Feedforward_neural_network

Watch this video too:-

Day 25

After understanding about the Feedforward Neural Network, on this day we’re going to take a look at Radial basis function Neural Network.

Radial basic functions consider the distance of a point with respect to the center. RBF functions have two layers, first where the features are combined with the Radial Basis Function in the inner layer and then the output of these features are taken into consideration while computing the same output in the next time-step which is basically a memory.

Take a look at this article:-

https://towardsdatascience.com/radial-basis-functions-neural-networks-all-we-need-to-know-9a88cc053448

Have a look at this video to better understand:-

Day 26

On this day, we’re gonna understand what a Kohonen Self Organizing Neural Network is.

The objective of a Kohonen map is to input vectors of arbitrary dimension to discrete map comprised of neurons. The map needs to be trained to create its own organization of the training data. It comprises either one or two dimensions. When training the map the location of the neuron remains constant but the weights differ depending on the value. This self-organization process has different parts, in the first phase, every neuron value is initialized with a small weight and the input vector.

Here’s a good article on Kohonen Self Organizing Neural Network:-

http://www.scholarpedia.org/article/Kohonen_network

Here’s a good a video on kohonen self organizing neural network:-

Day 27

The next neural network we’re gonna study is the Recurrent Neural Network(RNN).

The Recurrent Neural Network works on the principle of saving the output of a layer and feeding this back to the input to help in predicting the outcome of the layer.
Here, the first layer is formed similar to the feed forward neural network with the product of the sum of the weights and the features. The recurrent neural network process starts once this is computed, this means that from one time step to the next each neuron will remember some information it had in the previous time-step.

Take a look at this article to better understand:-

https://towardsdatascience.com/recurrent-neural-networks-d4642c9bc7ce

Also, look at this video to understand this neural network deeply:-

Day 28

On this day we’re gonna take a look at Convolutional Neural Network.

Convolutional neural networks are similar to feed forward neural networks, where the neurons have learnable weights and biases. Its application has been in signal and image processing which takes over OpenCV in the field of computer vision.

Take a look at this good article to understand Convolutional Neural Network:-

https://towardsdatascience.com/a-comprehensive-guide-to-convolutional-neural-networks-the-eli5-way-3bd2b1164a53

Also watch this great video:-

Day 29

The last neural network that we’re gonna take a look at is Modular Neural Network.

Modular Neural Networks have a collection of different networks working independently and contributing towards the output. Each neural network has a set of inputs that are unique compared to other networks constructing and performing sub-tasks. These networks do not interact or signal each other in accomplishing the tasks.

Take a look at this great article to know more about Modular Neural Network:-

https://www.sciencedirect.com/science/article/abs/pii/S0925231208005444

Also, take a look at this video:-

Day 30

We have completed our 30 days journey of Machine Learning. Now I’m sure that you have acquired a good and intelligent knowledge of Machine Learning and everything that goes with it.

But since you made it to the last, Here’s a link that contains over 200 Machine Learning concepts links. Keep this link with you and keep exploring it.

https://medium.com/machine-learning-in-practice/over-200-of-the-best-machine-learning-nlp-and-python-tutorials-2018-edition-dd8cf53cb7dc

And here’s the video of Sundar Pichai (Google’s CEO) talking about the future of Machine Learning:-

About Me..

Hey everyone! I’m Sparsh Sukralia, a React JS Web Developer, Blogger, Youtuber.

You can find me on Instagram here:-

https://www.instagram.com/codewithsparsh/

And here’s my Youtube channel:-

https://www.youtube.com/channel/UCVExTs1n5j3bD24btzgvMhA

Leave a Reply