If you’re going to run a test on rabbits, you have to decide how many rabbits you’ll use. This is…
Continue Readingsize
GPT-3, a giant step for Deep Learning and NLP?
“The diversity of tasks the model is able to perform in a zero-shot setting suggests that high-capacity models trained to…
Continue ReadingHow to estimate ODE solver error
This post brings together several themes I’ve been writing about lately: caching function evaluations, error estimation, and Runge-Kutta methods. A…
Continue ReadingFollow & Learn: Experiment Size With Python
at 80%. The plot below shows the distributions under null and test hypotheses. Analytical ApproachLet’s take the plot above and…
Continue ReadingOptimize Angular bundle size in 4 steps
There are tons of topics about improving your app’s performance, such as lazy loading, change detection, server side rendering, etc.…
Continue ReadingMaster Your Hypothesis Test: A tutorial on Power, Bootstrapping, Sample Selection, and Outcome Analysis.
This is a very nice sanity check, and the formula also gives us a P-Value. 6. Evaluating our P-ValueWhen we…
Continue ReadingSimplicity in the complexity
Let’s break down the term into “neuron” and “network”. To interpret “neuron”, we can think of it as a black…
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 ReadingSample size and correlation
As a rule of thumb, statisticians consider an r-value of 0. 7 to be strong. Let’s take a look at…
Continue ReadingBig O Notation (using Ruby)
Big O Notation (using Ruby)Daniel KoBlockedUnblockFollowFollowingApr 11Big O Notation allows us to calculate the worst possible runtime of an algorithm, or…
Continue ReadingHow Do You Know You Have Enough Training Data?
What Happens in the Case of Deep Learning?Figure 1. Figure 1 shows how the performance of machine learning algorithms changes…
Continue ReadingScala: Useful User Information + Why you should consider the Language
") } val arr = Array. fill(2097152)(0) tenMillionSearches(arr, 2097152)}Running the program above, we obtain the following results:Scala vs. C++Now we…
Continue ReadingPredicting the performance of deep learning models
Predicting the performance of deep learning modelsPower-law scaling explains how a model’s performance will change as we feed it more dataArchy de…
Continue ReadingBetter Heatmaps and Correlation Matrix Plots in Python
Finding the highest negative and positive correlations mean finding the strongest red and green. To do that I need to…
Continue ReadingHow production friendly and ready is your Angular app?
That number is sure to go up, if not significantly. 3. 9MB is pretty huge when Medium’s homepage, for example…
Continue ReadingThunderstruck: Disaster CNN visualization of AC power lines
What during all the training made it look there for being the most significant area?That being said, this prediction should…
Continue ReadingGo memory ballast: How I learned to stop worrying and love the heap
Go memory ballast: How I learned to stop worrying and love the heapRoss EngersBlockedUnblockFollowFollowingApr 10I’m a big fan of small code…
Continue ReadingWhich promotion should be used to increase sales? A fast-food chain’s marketing campaign case study
To answer this question, we will start by exploring the data and finalize by applying a multiple linear regression to…
Continue ReadingDeep learning to identify Malaria cells using CNN on Kaggle
Deep learning to identify Malaria cells using CNN on KaggleKaran BhanotBlockedUnblockFollowFollowingApr 5Photo by Kendal James on UnsplashDeep learning has vast ranging applications…
Continue ReadingPredicting Stock Price with LSTM
", df_ge. isna(). sum())Normalizing the dataThe data is not normalized and the range for each column varies, especially Volume. Normalizing data…
Continue ReadingElection Poll Simulation, Margin of Error and Central Limit Theorem with Python
Election Poll Simulation, Margin of Error and Central Limit Theorem with PythonWaldecir FariaBlockedUnblockFollowFollowingMar 14While learning about the Central Limit Theorem (CLT)…
Continue ReadingMezzFS — Mounting object storage in Netflix’s media processing platform
MezzFS — Mounting object storage in Netflix’s media processing platformNetflix Technology BlogBlockedUnblockFollowFollowingMar 6By Barak Alon (on behalf of Netflix’s Media Cloud Engineering…
Continue ReadingProblem Analysis of Code Jam to I/O for Women’19
(Think of some greedy approach)3. Sleep WalkingProblem Description -We have a 2-D grid with infinite number of unit cells. A person…
Continue ReadingData Science in the Trenches: Living w/ Small n
What can we do?”Well, there’s a couple of things that you can consider, all of which involve different kinds of…
Continue ReadingA Significant Answer to that Statistical Question
You will need buy-in to talk to more people now, so build up your stakeholders’ appetite for discovery by presenting…
Continue Reading