Hands-on Tutorials

Illustration of analysis and procedures used in hierarchical clustering in a simplified manner

Photo by Alina Grubnyak, Unsplash

In our previous article on Gaussian Mixture Modelling(GMM), we explored a method of clustering the data points based on the location of the sample in its feature vector space. In GMM, based on the distribution of data points in the system, we were able to assign the likelihood of every sample belonging to each cluster in a probabilistic manner.

But what if instead of just focussing on the concentration of distribution of the data points in the entire system, we wanted to quantitatively estimate the relation between every sample in the system and study how close each data point is…


Explanation of Gaussian Mixture Models and its underlying algorithm of Expectation-Maximization in a simplified manner

Photo by Aaron Burden, Unsplash

After you learn how to cluster the samples of unlabelled data points using the simplest clustering algorithm of k-means, we begin to see several shortcomings of k-means upon the application of this technique on a real dataset. The next step an ML engineer will take is to apply more sophisticated algorithms to understand various groupings(clusters) in his/her data samples and most likely this algorithm is going to be Gaussian Mixture Modeling (GMM). Due to the presence of open-source software and multiple ML frameworks like Scikit-learn, all it takes is just a couple of lines to make use of this algorithm…


Photo by h heyerlein on Unsplash

Presently, there is a major concern on the probability of the likelihood of having a global economic crisis.

In spite of the supposedly cautious mood adopted by few countries, nobody is willing to give a clear message on whether the next recession is just a week away or a year away. And then there are few others, who are giving indications that there is absolutely no economic slowdown at all.

Above all, the opinions of these financial gurus are changing daily from positive to negative outlook and even vice-versa. …


Any deep learning framework in order to be successful, has to provide a good collection of state of the art models, along with its weights trained on popular and widely accepted datasets. Many frameworks usually refer to this collection as Model Zoo. TensorFlow in it’s initial versions provided this model zoo through it’s TF-Slim framework. But TF-Slim’s usability for models was not intuitive and over the course of time, TF-Slim has also been deprecated.

TensorFlow, now has come up with a better framework known as TensorFlow Hub which is very easy to use and is well organised. With TensorFlow Hub…


In the previous article, I have demonstrated how to make use of Tensorflow’s Datasets and Iterators. There we had created Datasets directly from Numpy (or Tensors). Another methodology of creation of Dataset is with TFRecords. In this post, we will be exploring on what is a TFRecord, how to use it with Datasets and extract data with Iterators. We will venture into a very important issue but less documented topic of how to save images in TFRecord. We will also look into the common issue of TFRecord size getting bloated up.

What is a TFRecord?

TFRecord is an individual aggregated compact file summing up…


From the time I have started using Tensorflow, I have always been feeding the data to my graph during training, testing or inferencing using the feed_dict mechanism of Session. This particular practice has been advised by Tensorflow developers to be strongly discontinued either during the training or repeatedly testing same series of dataset. The only particular scenario in which feed_dict mechanism is to be used is during inferencing of data during deployment. The replacement of feed_dict has taken place with Dataset and Iterator. The dataset can be created either with Numpy array or TFRecords or with text.

In this post…


In this article, let us build an application of recognizing and classifying various types of hand gesture pose. The output of this application is shown in the image below.

Some examples of classified hand gesture poses

Some ML engineers may try to attempt this problem statement by collecting as many pictures as possible of various hand poses and build the neural network model from scratch. Another set of people may try to find existing models that do hand gesture classification and then retrain for the required set of hand poses. …


We at Y Media Labs have been working on implementing Artificial Intelligence in various sectors which brings value in our daily lives. One such field we have targeted is of Education sector. We have performed few experiments to recognize and localize objects in the images/videos and with this technological capability, we would like to leverage it to teach children about the flags of the various countries in the world. Check the below video to see what we are going to discuss about in this article.

Youtube link

Every year, with the vast improvements among the winners in ImageNet competitions, lots…


Recently, I have started learning about Artificial Intelligence as it is creating a lot of buzz in industry. Within these diverse fields of AI applications, the area of vision based domain has attracted me a lot. For that, I have been experimenting with deep learning mechanisms primarily involving usage of Convolutional Neural Network(CNN). The primary thing with all the experiments I have done till date has taught me that data which is used during training plays the most important role. In fact, it will not be wrong to state that AI has emerged again (after several AI winters) only because…


Real time database provides very nice platform for experimentation and dwelling onto your creativity. As the speed of necessity in fetching/getting the information increases along with the extra constraint of data changing all the time, real time databases have proved to be very useful.

Now in a massive real time database, it would be great if you are informed of the changes happening in certain part of data, where you are interested in, in real time, as the change happens. In design pattern, this model will be referred to as publisher-subscriber model.

There exists several third party cloud service providers…

Prasad Pai

An aspiring data scientist moving ahead with one step at a time.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store