This is a good question, and the answer to that is using callbacks. Callbacks: taking a peek into our model…
Continue Readingrate
Analysing the Effects of Brexit: A Statistical Approach
Analysing the Effects of Brexit: A Statistical ApproachDavid FarrugiaBlockedUnblockFollowFollowingJul 7Illustration by Sky NewsIn my humble opinion, one of the most powerful…
Continue ReadingA Comprehensive State-Of-The-Art Image Recognition Tutorial
we have covered many core concepts so far. Let’s continue…Let’s now train the model on our dataset,fit_one_cycle trains the model…
Continue ReadingFighting Churn With Data
Definitely not!So to reduce churn you really need to increase value the users receive but this is going to be…
Continue Reading10 New Things I Learnt from fast.ai Course V3
I just got to know this like only now. This is the fundamental of deep learning. If you have stacks…
Continue ReadingData Science Fundamentals — A/B Testing
It can happen because we are sampling. For example, if I picked 100 people at random from a large crowed…
Continue ReadingAn introduction to high-dimensional hyper-parameter tuning
As not intuitive as it might seem, this idea is almost always better than Grid Search. A little bit of…
Continue ReadingLaravel: There is a RateLimiter and you didn’t know
This class is not registered in the Service Container, but you can instance it using the app helper anywhere in…
Continue ReadingFinancial Reporting at Billion Dollar Scale — Exchange Rates
Financial Reporting at Billion Dollar Scale — Exchange RatesHow Airbnb handles exchange rates for financial reportingWanli YangBlockedUnblockFollowFollowingJun 5Authors: Wanli Yang, Ziheng Deng and…
Continue ReadingPreventing Discriminatory Outcomes in Credit Models
Preventing Discriminatory Outcomes in Credit ModelsValeria CortezBlockedUnblockFollowFollowingJun 5Machine learning is being deployed to do large-scale decision making, which can strongly impact…
Continue ReadingExploring Learning Rates to improve model performance in Keras
Exploring Learning Rates to improve model performance in KerasGuncha GargBlockedUnblockFollowFollowingJun 5The learning rate is a hyper parameter that controls how much…
Continue ReadingUncertainty + Visualization, Explained
Uncertainty + Visualization, ExplainedMidwest Uncertainty (MU) CollectiveBlockedUnblockFollowFollowingJun 4Jessica Hullman and Matthew Kay (the MU Collective). TLDR: The first in a…
Continue Readingktrain: A Lightweight Wrapper for Keras to Help Train Neural Networks
ktrain: A Lightweight Wrapper for Keras to Help Train Neural NetworksArun MaiyaBlockedUnblockFollowFollowingJun 3ktrain is a library to help build, train, debug,…
Continue Reading1st Place Solution for Intel Scene Classification Challenge
1st Place Solution for Intel Scene Classification ChallengeHosted by Analytics VidhyaAfzal SayedBlockedUnblockFollowFollowingJun 2IntroductionProblemYou are provided with a dataset of ~25k…
Continue ReadingChurn Prediction
Data Driven Growth with PythonChurn PredictionChurn Prediction with XGBoost Binary ClassificationBarış KaramanBlockedUnblockFollowFollowingMay 25This series of articles was designed to explain how…
Continue ReadingLearning Analytics
Learning AnalyticsSambit DasBlockedUnblockFollowFollowingMay 25Wow . This is a fascinating topic to delve into. Using the Eight step methodology for Workforce analytics…
Continue ReadingHow, When and Why Should You Normalize / Standardize / Rescale Your Data?
How, When and Why Should You Normalize / Standardize / Rescale Your Data?Swetha LakshmananBlockedUnblockFollowFollowingMay 16Before diving into this topic, lets first…
Continue ReadingHow, When and Why Should You Normalize/Standardize/Rescale Your Data?
How, When and Why Should You Normalize/Standardize/Rescale Your Data?Swetha LakshmananBlockedUnblockFollowFollowingMay 16Before diving into this topic, lets first start with some definitions.…
Continue ReadingROC Curves and the Efficient Frontier
In that case you catch every good investment but incur a significant cost. Also note that in the example ROC…
Continue ReadingScaling Transformer-XL to 128 GPUs
Scaling Transformer-XL to 128 GPUsBen MannBlockedUnblockFollowFollowingMay 9Ben Mann, Yaroslav Bulatov, Darius LamTL;DR: we made Transformer-XL train efficiently on 128 GPUs on…
Continue ReadingKnow Your Metrics
We can’t say anything without doing a deep-dive analysis. Monthly Active CustomersTo see the details Monthly Active Customers, we will…
Continue ReadingAn intuitive understanding of the LAMB optimizer
are simply linear interpolations (β * x₀ + (1 — β) * x₁) of the gradients and their variances, which gives us…
Continue ReadingHistopathological Cancer Detection with Deep Neural Networks
Histopathological Cancer Detection with Deep Neural NetworksAntonio de PerioBlockedUnblockFollowFollowingApr 20(Note: The related Jupyter notebook and original post can be found here:…
Continue ReadingHow to assess a binary Logistic Regressor with scikit-learn
How to assess a binary Logistic Regressor with scikit-learnBookmark this python function that makes assessing your binary classifier easy. Greg…
Continue ReadingHow to interpret a binary Logistic Regressor with scikit-learn
How to interpret a binary Logistic Regressor with scikit-learnGreg ConditBlockedUnblockFollowFollowingApr 17Functionality OverviewLogistic Regression is a valuable classifier for its interpretability.…
Continue Reading