Machine learning and statistics with python

 Introduction: On a very bright friday, I don't have any specific hard task in my hands and therefore decided to explore a linkedin learning course. I would like to thank my current employer at the time of writing this blog; IQuanti for availing us the free linkedin learning.  In this post, we are going to review and provide key points from the course about learning python data structures. It is designed and created by Erin allard. Now, let's dive in. First concept: Abstract data types: What is abstract data types? "abstract data types are abstract theoretical computer science concept which defines what type of data a data structure can hold and how can we interact with that data." In case of creating new abstract data types, we have to therefore define both the data and ways to interact with it. But in the course, we are going to explore stack, queues and other well established structures; for which the formats are already well known.  It is also important to un...

        Exploring automl and pandas profiling using titanic dataset                               project and writing: shyambhu mukherjee Introduction: In this project, we created a kaggle notebook on the titanic dataset and explored two new items: (1) sberbank light automl library (2) pandas profiling In this blog post, I am going to describe the project; different code patches and how the whole thing worked out. Pandas profiling to start: If you don't know what is pandas profiling, then let me introduce to it. Basically pandas dataframe has a describe attribute; which let's you see the count,mean, median, 75%, and max of the columns in the dataframe. The pandas profiling is an extended version of that; which sort of automates the whole task of exploring and creating a large number of eda outputs.  In short, here are the things which pandas profiling does: (1) create bas...

A brief history of CNN: Convolutional neural networks is one of the most famous neural network architectures which are currently used in deep learning practices and researches. The concept of CNN came into existence from the long line of research which all started with the finding that animal brains have visual receptors with high local similarities of their reception and high overlap of their observation area. This then originated the concept of neurocognitron; and slowly through a decades of research the other concepts related to cnn, such as convolutional layer, spatial invariance, pooling layer and other properties came into picture. In the beginning of 2000, K.chellapia et al. created the final breakthrough; which was a gpu implementation of CNN. This made people realize that how with immense computational possibilities CNNs can come up to great works. There have been many development upon different breakthrough researches. We will discuss them later in this article. What is CN...

 Introduction: Activation functions are one of the most important components of a neural network model. Activation functions instill non-linearity into neural networks and also helps to suppress noisy data and improve signals where needed. The early idea of activation functions came into the engineering field via biological censoring of informations and how neurons stay inactive on some signal level and then activate on more than that. This phenomenon motivated early scientists to let the artificial neurons also behave in certain ways which leads it to emphasis or suppress based on different signal values.  But in current trends, activation functions are mostly motivated from mathematical point of views or even optimization or purely technical reasons. We will explore some of the most famous activation functions in this blog; will try to see why they were motivated and how/where they can become important. Summary of the article: In this article, we will explore activation fu...

 Introduction: Bort, is the new and more optimized version of BERT; which came out this october from amazon science. I came to know about it today while parsing amazon science's news on facebook about bort. So Bort is the newest addition to the long list of great LM models with extra-ordinary achievements.  Why is Bort important? Bort, is a model of 5.5% effective and 16% total size of the original BERT model; and is 20x faster than BERT, while being able to surpass the BERT model in 20 out of 23 tasks; to quote the abstract of the paper,  ' it obtains performance improvements of between 0 . 3% and 31%, absolute, with respect to BERT-large, on multiple public natural language understanding (NLU) benchmarks. ' So what made this achievement possible? The main idea behind creation of Bort is to go beyond the shallow depth of weight pruning, connection deletion or merely factoring the NN into different matrix factorizations and thus distilling it. While methods like know...

 Pose-estimation using OpenCV                written by: Dinesh Gitae, Rohini shinde, shyambhu mukherjee Pose-estimation is a classic computer vision task where we detect the pose of a human face or the body; and we decide different parameters or detect certain caricatures from that. In the mentoring effort from mentorbruh, dinesh and rohini took a opencv pose-estimation, completely understood the code and modified it to detect their own face pose via opencv. While dinesh completed it from local, rohini used a colab version to do the task. In this post, we will go through the code and understand it to the most tiny details; so that you can recreate the task or at least use such pose-estimation tasks. Summary of the article: In this article, first we introduce the reader to what is a pose-estimation task and what are the different models currently available in market to do the task. Then we quickly will go to the example and we will thorough...