Geek blog series - part 3
29 juli 2019 [04:07], 296 views
Door Redactie

Geek blog series - part 3

In this ‘Geek blog series’ these 'Geeks’ share their expertise and insights on the latest AI and Analytics topics. Below you will find the third part of this series.

Image classification? Use DLPy

By Jaimy van Dijk

Everybody is busy nowadays. Some might say that we need better work-life management. I say, let’s focus on automating some of our work! Take for instance all kind of controlling tasks, such as controlling if the usage of the company logo in vlogs and presentations is okay. Or controlling whether all products are straight on the packaging line so that the machine can pack them correctly. But there is good news. You can automate these tasks with computer vision, which means: extracting information from images using SAS DLPy, which stands for SAS Deep Learning in Python. This allows users to build deep learning models using friendly high-level API’s.

To show you how this works, we build a deep learning model based on Conventional Neural Networks (CNN) for image classification called: Geek/No Geek (also read this blog). We learned the model that geeks often do dress a bit strange. They wear striking glasses, suspenders, bowties and other eye-catching items. Using these attributes the model can classify people to be geeks or not. 

Using model interpretation techniques we can see that the model focuses on the face, presumably to find glasses, and on bright colors. Of course, you need to monitor the model over time. Since fashion changes the model will need to change over time as well.

I wish you good luck in training your own model for image classification. Questions? Don’t hesitate to reach out to me via LinkedIn.

LIME and ICE: The Secret Ingredients in your AI Cocktail

By Véronique Van Vlasselaer

The world of Machine Learning and Artificial Intelligence is growing more rapidly than ever before. Creative AI ideas sprout at an unbeatable pace, organizations are exploring the new emerging opportunities of Machine Learning and AI. Without realizing, machines are making millions of automated decisions without any human intervention to date, facilitating and augmenting people’s day-to-day life. But then the question arises: can we trust decisions made by AI? The most powerful algorithms that steer our daily life are typically so-called black box models. These are models that we as human beings cannot understand easily. The rationale and the logic of each decision is hidden in (often) billions of mathematical formulas, which are hard to unravel. On the other hand, we have white box models, where the logic behind each decision is easily explainable. Unfortunately, the performance of those white box models is often unsatisfactory. It seems that the modern data scientist has to make an impossible choice: a choice between accuracy and interpretability.

But is that true? Do we have to choose between the accuracy of a black box model on the one hand and explainability, fairness, accountability and trustworthiness of white box models on the other hand? Can’t we have both: explainable and accurate models? Yes, we can. Nowadays, lots of academic research is centered around the interpretability of black box models. Typically, interpretability techniques can be classified into two categories:
(1) techniques to explain the prediction of each individual observation.
(2) techniques that reveal the impact of each of the inputs or variables to the prediction.
And within SAS you have many options for this, amongst which LIME and ICE.

On individual observation level, you can use LIME. This stands for Local Interpretable Model-agnostic Explanations. For each individual prediction it generates an explanation: why did an observation receive that prediction? More specifically, LIME will fit for each observation a local model using the predicted value of the observation and nearby observations. The local model is a white box model, typically a LASSO regression. LIME will report on the values of the coefficients for the parameter estimates of the variables when using such a localized linear regression model.

Read also my blog about the GeekNoGeek App that we have developed to calculate someone’s geekiness score (i.e., a probability on how geeky you are) based on their profile picture. 

To explain the impact of the predictors to the prediction you can use ICE, which stands for Individual Conditional Expectation. ICE analyses what would happen to the predicted value of one observation if we change the value of one of the input variables. Take for instance color: what happens with the result if you adjust the color intensity of your picture?

Are you struggling with explaining the results of your black box models and need some help? Feel free to reach out to me via LinkedIn or Twitter.

 

Reacties

SAS is nummer één op het gebied van advanced en predictive analytics volgens IDC
26 september 2018 [10:43], 1960 views

SAS is nummer één op het gebied van advanced en predictive analytics volgens IDC

SAS overtreft opnieuw alle advanced en predictive analytics leveranciers, volgens het IDC-rapport.

 

Lees meer  

Ethisch raamwerk rondom AI-gebruik
19 september 2018 [04:24], 3689 views

Ethisch raamwerk rondom AI-gebruik

Organisaties werken aan een meer ethisch en verantwoordelijk gebruik van artificial intelligence Onderzoek van SAS, Accenture, Intel en Forbes Insights wijst uit dat [...]

 

Lees meer  

Ziekenhuis Gelderse Vallei zet stap in de wereld van zorginnovatie
17 september 2018 [10:00], 1798 views

Ziekenhuis Gelderse Vallei zet stap in de wereld van zorginnovatie

Ziekenhuis Gelderse Vallei maakt al ruim twaalf jaar gebruik van de analytische software van SAS. SAS Visual Analytics helpt met geavanceerde analyses waarmee het ziekenhu [...]

 

Lees meer  

Democratiseer data, geef iedereen zijn eigen analytics
9 augustus 2018 [10:00], 1888 views

Democratiseer data, geef iedereen zijn eigen analytics

Digitale transformatie, wat is dat nu eigenlijk? De woorden worden te pas en te onpas in de mond genomen zonder het concreet te maken.

 

Lees meer  

Hoe verandert de technologische ontwikkeling de strategie van toezicht en handhaving
27 juli 2018 [10:53], 4439 views

Hoe verandert de technologische ontwikkeling de strategie van toezicht en handhaving

Big data, data analytics, Internet of Things, cryptomunten, blockchain, kunstmatige intelligentie, FinTech en robotisering spelen een steeds belangrijkere rol in het maats [...]

 

Lees meer  

Hoe verschillende rollen elkaar ondersteunen in de analytics lifecycle
4 juli 2018 [03:53], 1623 views

Hoe verschillende rollen elkaar ondersteunen in de analytics lifecycle

We praten veel over vaardigheden, en met name over het belang van het ontwikkelen van nieuwe vaardigheden om breder en beter gebruik van analytics mogelijk te maken. [...]

 

Lees meer  

Hoogtepunten van de eerste SAS Data Science & Analytics Day
20 juni 2018 [11:37], 1220 views

Hoogtepunten van de eerste SAS Data Science & Analytics Day

Tijdens de eerste SAS Data Science & Analytics Day met als thema ‘Welcome to the Analytics Economy’ werd duidelijk dat data inmiddels onmisbaar is in onze samenl [...]

 

Lees meer  

Innovaties in een data gedreven samenleving
13 juni 2018 [09:00], 3950 views

Innovaties in een data gedreven samenleving

Innovaties in een data gedreven samenleving: van een grotere overlevingskans bij vroeggeboortes tot een leven lang genieten van voetbal. Op donderdag 31 mei vond de [...]

 

Lees meer  

Gezondheidszorg is early adopter in toepassen van AI
11 juni 2018 [10:17], 1327 views

Gezondheidszorg is early adopter in toepassen van AI

Artificial Intelligence is waarschijnlijk het grootste buzzwoord van 2017 en 2018, en terecht! De gezondheidszorg lijkt echter een sector die, als early adopte [...]

 

Lees meer  

Hoe DHL meer grip krijgt op veranderende omstandigheden
8 mei 2018 [11:26], 4424 views

Hoe DHL meer grip krijgt op veranderende omstandigheden

Logistiek dienstverlener DHL onderzoekt de mogelijkheden om data analytics toe te passen op operationeel niveau om direct in te kunnen spelen op veranderende omstand [...]

 

Lees meer