Gabriel Cypriano

Data scientist. More at gabrielcs.me

20 Followers | 54 Following

Follow

Gabriel Cypriano

11 days ago

If we perform an EDA on the whole dataset (including the test dataset) and use that info to come up with some feature engineering than we could also suffer from data leakage.

There are many ways of imputing the values, mean, or median. It is up to you how to do it but make sure to calculate the imputation statistics only on the training data to avoid data leakage of your test set.

Common mistakes when carrying out machine learning and data science

kdnuggets.com

Gabriel Cypriano

22 days ago

I would suggest also more generally:

Gradient Boosting
Random Forest
Support Vector Classifier
Extra Trees
Logistic Regression

Start With Gradient Boosting, Results from Comparing 13 Algorithms on 165 Datasets

machinelearningmastery.com

Gabriel Cypriano

22 days ago

Great overview of internals.

LightGBM and XGBoost Explained

mlexplained.com

Gabriel Cypriano

49 days ago

Visualizing Machine Learning Thresholds to Make Better Business Decisions

Visualizing Machine Learning Thresholds to Make Better Business Decisions

blog.insightdatascience.com

Gabriel Cypriano

52 days ago

there is no need to spend years obtaining a PhD in order to practise deep learning. Creating software that learns can be taught as a craft, not as a high intellectual pursuit to be undertaken only in an ivory tower

New schemes teach the masses to build AI

economist.com

Gabriel Cypriano

57 days ago

Under SSPL, users can still change and redistribute the software, but it explicitly states that if a person or a company wants to publicly offer MongoDB as a service, they must open source that service -- meaning they must make the code available to everyone for free. Otherwise, they must obtain a commercial license.

Two software companies, fed up with Amazon, Alibaba and other big cloud players, have a controversial new plan to fight back

businessinsider.com

Gabriel Cypriano

71 days ago

Fastai is the first deep learning library to provide a single consistent interface to all the most commonly used deep learning applications for vision, text, tabular data, time series, and collaborative filtering. This is important for practitioners, because it means if you’ve learnt to create practical computer vision models with fastai, then you can use the same approach to create natural language processing (NLP) models, or any of the other types of model we support

Fast.ai launches fastai v1, a deep learning library for PyTorch

venturebeat.com

Gabriel Cypriano

71 days ago

fastai v1 for PyTorch: Fast and accurate neural nets using modern best practices

fast.ai

Gabriel Cypriano

85 days ago

What gives researchers hope is the striking resemblance the olfactory system’s structure bears to other regions of the brain across many species, particularly the hippocampus, which is implicated in memory and navigation, and the cerebellum, which is responsible for motor control. Olfaction is an ancient system dating back to chemosensation in bacteria, and is used in some form by all organisms to explore their environments.

“It seems to be closer to the evolutionary origin point of all the things we’d call cortex in general,” Marblestone said. Olfaction might provide a common denominator for learning. “The system gives us a really conserved architecture, one that’s used for a variety of things across a variety of organisms,” said Ashok Litwin-Kumar, a neuroscientist at Columbia. “There must be something fundamental there that’s good for learning.”

Artificial Intelligence Has a Strange New Muse: Our Sense of Smell

wired.com

Gabriel Cypriano

88 days ago

7 Things to Start Being More Productive, Today

medium.com

Gabriel Cypriano

90 days ago

TODOS devem olhar para fora.

Qual a diferença entre Product Managers e Product Owners, segundo Marty Cagan

somostera.com

Gabriel Cypriano

93 days ago

It’s important to note that a chapter lead is not a manager of the team, but is a manager of a domain that spans across teams

Scaling Agile Development at Spotify

academy.realm.io

Gabriel Cypriano

93 days ago

your main task as a chapter lead is to make sure your chapter members are happy. Sounds shallow? Easy? Think one more time!! This is the hard and most crucial part. It is your responsibility to help your chapter members with their development, both hard skills as well as the soft ones. Help them exploit their strengths and handle their weaknesses. Make sure they are properly equipped to perform their job the best they can. A happy chapter member is the best compliment a chapter lead can get!

Team Lead versus Chapter Lead: the 5 biggest differences

agileadventures.net

Gabriel Cypriano

93 days ago

With this model, changing teams does not mean changing your manager, and dissolving a team doesn’t leave a manager looking for a new role

The Spotify model: how to create, dissolve, and remix teams to be more dynamic and more innovative

agileandchange.com

Gabriel Cypriano

93 days ago

One can ‘t exist without the other. No productive squad without skilled resourcing from relevant chapters. No point in having chapters when there’s no need for the expertise.

Squad versus Chapter: 4 greatest differences

agileadventures.net

Gabriel Cypriano

99 days ago

Google launches new search engine to help scientists find the datasets they need

theverge.com

Gabriel Cypriano

107 days ago

Why feature weights in a machine learning model are meaningless

hackernoon.com

Gabriel Cypriano

116 days ago

Netflix is the latest company to try bypassing Apple’s app store

marketwatch.com

Gabriel Cypriano

120 days ago

Spotify’s $30 Billion Playlist for Global Domination

medium.com

Gabriel Cypriano

122 days ago

I've seen a talk about all the cool things Salesforce does with TransmogrifAI. Highly recommend checking it out

Open Sourcing TransmogrifAI

engineering.salesforce.com

Gabriel Cypriano

130 days ago

the examples contradict the notion that you have to either select an explainable model or a more complex – and therefore more accurate – one. The explanations given using an accurate and complex Gradient Boosting Machine model were as clear as a linear model could get and made total intuitive sense. This also highlights the strengths of SHAP in providing accurate and consistent explanations.

Model Interpretability with SHAP – F1 predictor

f1-predictor.com

Gabriel Cypriano

130 days ago

Traditional feature importance algorithms will tell us which features are most important across the entire population, but this one-size-fits-all approach doesn’t always apply to each individual customer. A factor that is an important driver for one customer may be a non-factor for another.

Demystifying Black-Box Models with SHAP Value Analysis

medium.com

Gabriel Cypriano

131 days ago

Opinion: These 5 tech stocks are in a dot-com-like bubble (and they aren’t all FAANGs)

marketwatch.com

Gabriel Cypriano

148 days ago

If the first thing we do is poke around in our data, our decision will be, at best, something I like to call data-inspired.

Data-Driven? Think again

hackernoon.com

Gabriel Cypriano

239 days ago

Someone transferred $99 million in litecoin — and it only cost them $0.40 in fees

Someone transferred $99 million in litecoin — and it only cost them $0.40 in fees

businessinsider.com

Gabriel Cypriano

242 days ago

A.I. Researchers Are Making More Than $1 Million, Even at a Nonprofit

nytimes.com

Gabriel Cypriano

269 days ago

Think Your Company Needs a Data Scientist? You're Probably Wrong.

entrepreneur.com

Gabriel Cypriano

293 days ago

If a machine knew how to define a contract automatically, and put it on some system that other systems could solve, there is a potential for now machine learning systems solving problems autonomously at a certain level

Algorithmia launches Ethereum-based AI competition

venturebeat.com

Gabriel Cypriano

304 days ago

‘Humans Die. Cryptocurrencies Don’t’: Why You Should Begin Planning Your Estate Immediately

ccn.com

Gabriel Cypriano

305 days ago

Sky-High Salaries Are the Weapons in the AI Talent War

bloomberg.com

Gabriel Cypriano

340 days ago

AI learns how to fool speech-to-text. That’s bad news for voice assistants

thenextweb.com

Gabriel Cypriano

342 days ago

Exclusive: What Fitbit's 6 billion nights of sleep data reveals about us

finance.yahoo.com

Gabriel Cypriano

368 days ago

Google's AI found an overlooked exoplanet, and now our Solar System is tied for biggest

theverge.com

Gabriel Cypriano

405 days ago

bloomberg.com

Gabriel Cypriano

428 days ago

Apple thinks it's about to change your world with its new iPhone feature, and it could be right

independent.co.uk

Gabriel Cypriano

435 days ago

Doing Data Science at Twitter

medium.com

Gabriel Cypriano

435 days ago

Doing Data Science Right — Your Most Common Questions Answered

firstround.com

Gabriel Cypriano

438 days ago

Google Assistant now sounds more realistic thanks to DeepMind

androidauthority.com

Gabriel Cypriano

438 days ago

Udacity Launches a ‘Learn ARKit’ Course Created in Collaboration with Unity

roadtovr.com

Gabriel Cypriano

448 days ago

"Electrification enables autonomy, and autonomy accelerates adoption of electrification".

How Electric Cars Can Create the Biggest Disruption Since the iPhone

bloomberg.com

Gabriel Cypriano

449 days ago

The new React license will take effect later this week with the launch of React 16

Facebook re-licenses React under MIT license after developer backlash

thenextweb.com

Gabriel Cypriano

454 days ago

If companies want to get value from their data, they need to focus on accelerating human understanding of data, scaling the number of modeling questions they can ask of that data in a short amount of time, and assessing their implications.

Why You’re Not Getting Value from Your Data Science

hbr.org

Gabriel Cypriano

458 days ago

ARCore is launching on the Pixel and Galaxy S8 (running 7.0 Nougat and above) to start

Google shows off ARCore, its answer to Apple’s ARKit

techcrunch.com

Gabriel Cypriano

459 days ago

Video: A sneak peak at iOS 11 Augmented Reality at the Apple Park Visitor Center

appleinsider.com

Gabriel Cypriano

459 days ago

Cryptocurrencies comparison.

visualcapitalist.com

Gabriel Cypriano

459 days ago

"A post-smartphone world is all about the shift to Augmented Reality with glasses that 50+% of people in the US wear everyday"

Gene Munster Says Apple's Future Is Shifting to Wearables

bloomberg.com

Gabriel Cypriano

459 days ago

Outer Space Is About to Get a Whole Lot Closer

bloomberg.com

Gabriel Cypriano

461 days ago

manufacturing two genuinely different versions of a product costs a lot more. The challenge is to predict the willingness to pay of customers while making them feel as if they have benefited from value – or better features. “If you have one product and the price is too high, people don’t buy it. But if it’s too low, you don’t exploit some customers’ willingness to pay,” he says.

How did Tesla make some of its cars travel further during Hurricane Irma?

theguardian.com

Gabriel Cypriano

463 days ago

You should assume that whatever specific libraries and software you learn today will be obsolete in a year or two. Just think about the number of changes of libraries and technology stacks that occur all the time in the world of web programming — and yet this is a much more mature and slow-growing area than deep learning. So we strongly believe that the focus in learning needs to be on understanding the underlying techniques and how to apply them in practice, and how to quickly build expertise in new tools and techniques as they are released.

Introducing Pytorch for fast.ai · fast.ai

fast.ai

Gabriel Cypriano

463 days ago

Facebook and Microsoft introduce new open ecosystem for interchangeable AI frameworks

research.fb.com

Like this set of items on Pocket? Share with friends.