They more often than not base their decisions on which teams they support and on which EPL players are the…
Continue ReadingDeep Learning Model Training Loop
Deep Learning Model Training LoopImplementing a simple neural network training loop with Python, PyTorch, and TorchVision.Several months ago I started exploring…
Continue ReadingPhysics-guided Neural Networks (PGNNs)
They present two approaches for this: (1) using physics theory, they calculate additional features (feature engineering) to feed into the…
Continue ReadingObserving is not intervening
For this, we need to select the sample corresponding to Drug 2 = NoNo Drug 2 tableand calculate the probability of…
Continue ReadingSimpson’s Paradox and Interpreting Data
Simpson’s paradox highlights one of my favourite things about data: the need for good intuition regarding the real world and…
Continue ReadingPreparing for in-person data science interviews
So, while large part of what I am going to write is generic and hopefully useful for everyone, some parts…
Continue ReadingHex – Creating Intelligent Adversaries (Part 2: Heuristics & Dijkstra’s Algorithm)
In a way, it can be considered a shortcut.tl;dr A heuristic is an approximation of the exact solution.To get a…
Continue ReadingObject Detection with Voice Feedback — YOLO v3 + gTTS
API: The class prediction of the objects detected in every frame will be a string e.g..Output: We will also obtain…
Continue ReadingRegex on the Texts of Harry Potter
Each tuple in the list corresponds to a chapter in the book and takes the form (‘C H A P…
Continue ReadingProbability and Statistics explained in the context of deep learning
Probability and Statistics explained in the context of deep learningPhoto by Josh Appel on UnsplashThis article is intended for beginners in deep…
Continue ReadingCar De-registrations in Singapore: Can they be Predicted?
The data is in monthly series, with the first time point being Feb 1990..For illustration, the training and test data…
Continue ReadingThe History of the Big Ten Football Conference
The Illini swept the conference in 2001 — outscoring Penn State, Ohio State, and Wisconsin by 5, 12 points, 7 points, respectively..This…
Continue ReadingLinear Correlations of 2016 Presidential Election Data to Various Arbitrarily Chosen Data
people voting for Trump (%):Figure 2.: A scatterplot relating age adjusted mortality rate due to malignant neoplasms (i.e. cancer, in incidents…
Continue ReadingTensorFlow Filesystem — Access Tensors Differently
The motivation I had behind writing TFFS (TensorFlow File System) can be shared by anyone who has used tensorflow, including…
Continue ReadingReview: ResNeXt — 1st Runner Up in ILSVRC 2016 (Image Classification)
And ResNeXt becomes the 1st Runner Up of ILSVRC classification task.ILSVRC 2016 Classification Ranking http://image-net.org/challenges/LSVRC/2016/results#locResidual Block in ResNet (Left), A…
Continue ReadingData Scientists, The one Graph Algorithm you need to know
Let us start with a simple graph class written in Python to start up our exploits with code.This post will…
Continue ReadingShortcoming of Under-sampling Algorithms: CCMUT and E-CCMUT
Shortcoming of Under-sampling Algorithms: CCMUT and E-CCMUTNavoneel ChakrabartyBlockedUnblockFollowFollowingDec 7In one of my my previous article, “Under-sampling : A Performance Booster on Imbalanced…
Continue ReadingImplementing ResNet with MXNET Gluon and Comet.ml for image classification
Implementing ResNet with MXNET Gluon and Comet.ml for image classificationCecelia ShaoBlockedUnblockFollowFollowingDec 6In this tutorial, we will illustrate how to build…
Continue ReadingANOVA explained without math: Why analyze variances to compare means?
There will be no formulas.ANOVA is used when we want to compare means among three or more groups (with only…
Continue ReadingHow to Write a Jupyter Notebook Extension
(Source)How to Write a Jupyter Notebook ExtensionMake the Jupyter Notebook your playgroundWilliam KoehrsenBlockedUnblockFollowFollowingDec 8Jupyter Notebook Extensions are simple add-ons which…
Continue ReadingThe Tragedy of #OpenData
But a great way to learn about The Tragedy of The Commons.The Tragedy of #OpenDataIt Is A Commons Tale (no, that…
Continue ReadingWhy Kaggle will NOT make you a great data-scientist
Why Kaggle will NOT make you a great data-scientistPranay DaveBlockedUnblockFollowFollowingDec 6Want to be an Eagle or Kaggle data scientist ?There is…
Continue ReadingData network effects for an artificial intelligence startup
Data network effects for an artificial intelligence startupShifting attention from product and data collection to network and data sharingPeter ZheginBlockedUnblockFollowFollowingDec 8Photo…
Continue ReadingA short guide to using Docker for your data science environment
A short guide to using Docker for your data science environmentSay goodbye to OS troubles and hello to portability!NileshBlockedUnblockFollowFollowingDec 8WHYOne…
Continue ReadingHow To Ask The Right Questions As A Data Scientist
How To Ask The Right Questions As A Data ScientistTo Define a Problem StatementAdmond LeeBlockedUnblockFollowFollowingDec 7Before we talk about how…
Continue Reading