#Machine_Learning : détection d’anomalies
▻https://makina-corpus.com/blog/metier/2019/machine-learning-detection-anomalies
Comment détecter des anomalies dans vos datasets en utilisant des algorithmes de machine learning.
#Machine_Learning : détection d’anomalies
▻https://makina-corpus.com/blog/metier/2019/machine-learning-detection-anomalies
Comment détecter des anomalies dans vos datasets en utilisant des algorithmes de machine learning.
How we used #ai to hybridize humans with cartoon animals and made a business out of it.
▻https://hackernoon.com/how-we-used-ai-to-hybridize-humans-with-cartoon-animals-and-made-a-busin
Have you ever imagined yourself as a cartoon character? Well, now this is more than real.We are a team of 20 engineers and art designers who have developed a machine learning technology that morphs human faces with animated characters.The process starts by constructing a user’s 3D face model from just a single selfie shot. Importantly, our technology even works with older, regular smartphone cameras. With this single photo, our neural network builds a 3D mesh of the user’s head that looks like this:The neural network regresses a 3D model from a 2D photoNext, 3 other neural networks swing into action. The first draws eyebrows, the second detects and matches eye color, and the third detects and draws glasses if the user is wearing them. When these elements are ready, we morph the user with (...)
Prédiction du taux de monoxyde de carbone à Madrid - intérêt d’une approche #Deep_Learning
▻https://makina-corpus.com/blog/metier/2019/qualite-de-lair-a-madrid
Dans cet article nous montrons comme utiliser les bibliothèques stars de l’éco-système scientifique en Python pour analyser des données publiques sur la qualité de l’air à Madrid. Nous verrons comment identifier les problèmes liés à ces données. Puis nous comparerons deux approches en #Machine_Learning : AutoSklearn et les réseaux de neurones de type LSTM.
Prédiction du taux de monoxyde de carbone à Madrid - intérêt d’une approche #Deep_Learning
▻https://makina-corpus.com/blog/metier/2018/qualite-de-lair-a-madrid
Dans cet article nous montrons comme utiliser les bibliothèques stars de l’éco-système scientifique en Python pour analyser des données publiques sur la qualité de l’air à Madrid. Nous verrons comment identifier les problèmes liés à ces données. Puis nous comparerons deux approches en #Machine_Learning : AutoSklearn et les réseaux de neurones de type LSTM.
Top 10 Trending Artificial Intelligence Frameworks and Libraries
▻https://hackernoon.com/top-10-trending-artificial-intelligence-frameworks-and-libraries-69ba590
Artificial Intelligence is the future of the programming world. More and more developers, seeing the growing demand for #ai technologies, familiarize themselves with this science. And when you start learning AI and how it can be implemented in programming, the first question which comes to mind is “What are the best languages/frameworks/libraries to use?” That’s exactly what we will cover today in this review of the top 10 AI frameworks and libraries every programmer must know.Let’s be honest, some languages are just not well fit for AI. For example, many Ruby developers who are into AI abandon their most beloved language and switch to Python because the latter is better suited for this purpose. However, the languages which are quite AI-friendly such as C++ offer an abundance of frameworks (...)
#ai-framework #machine-learning #ai-libraries #artificial-intelligence
Deep Learning Software Setup: CUDA 10 + Ubuntu 18.04
▻https://hackernoon.com/deep-learning-software-setup-cuda-10-ubuntu-18-04-15548cefa30?source=rss
Deep Learning Software Setup: CUDA 10 + Ubuntu 18.04 (Part 2 of a $4000 RTX 2080Ti (MSI) DL box series)Part 2 of getting our First Deep Learning BuildIn the previous writeup, I had given a brief walkthrough of the parts that I had picked for “Neutron” and about the reasons for getting it assembled from a third party retailer: “Ant-PC”.In this blog, I’ll share the step by step instructions that for setting up software on an #nvidia-based “Deep Learning Box”.Overview:For storage, I have 2 Drives:Samsung 970 Pro NVMe M.2 512GB2TB HDDMy retailer had been kind enough to install windows as per my request on a 500GB partition made on the HDD.Ubuntu 18.04 InstallationFor Neutron, I was going to have Ubuntu 18.04 installed on the M.2 drive with Swap space allocated on it as well, plus the extra space left (...)
#artificial-intelligence #machine-learning #deep-learning #servers
Kick Start Your Side Projects With Public #data
▻https://hackernoon.com/kick-start-your-side-projects-with-public-data-f6f728a1a6e5?source=rss--
Otto Knows How To Kick StartAre you stuck looking for a project so that you can start building an app?Are you a beginner looking to get into #programming?Are the projects that you are following on tutorial sites too boring for you?If you answered yes to any of these questions, you must be stumped and are eagerly seeking to keep your flame burning for coding before it runs out.Starting From Scratch SucksI am a big advocate for side projects, so much so that it helped me secure an internship with a hyper growth startup! Therefore, I wanted to start off the New Years guns blazing with pet projects, so I decided to create an an API for one of my favorite arcade fighting games Marvel VS Capcom 2.Now that I have finished those projects, I am back to the drawing board, so I decided that it was time (...)
Neutron : A $4000 RTX 2080Ti (MSI) Deep Learning box (8700k/64GB/2080Ti)
▻https://hackernoon.com/neutron-a-4000-rtx-2080ti-msi-deep-learning-box-8700k-64gb-2080ti-82db25
Part 1 of 2 of getting our First Deep Learning BuildDisclaimer: While I’ve chosen components based from different manufacturers, none of these are sponsored.Also Note that the prices are based in India. The components here might be comparatively much more expensive depending on your country.But well, If MSI-you’re reading this. I have a few more slots to populate with more RTX cards ;)Since the launch of My little company Neuroascent that I’ve Co-founded along with Rishi Bhalodia about a few months ago, We’ve reached a stage that now we’re ready to invest in a “Deep Learning Rig”.We’re fast.ai fellows and fans and Jeremy Howard advises building a “Deep Learning Box” whilst doing the Part 2 of their MOOC.We’ve chosen to dedicate our time to #fastai thoroughly and then shift to other paths.After (...)
#tech #artificial-intelligence #deep-learning #machine-learning
Machine Learning #notes 2
▻https://hackernoon.com/machine-learning-notes-2-c0fe5a841c54?source=rss----3a8144eabfe3---4
From Machine Learning -Tom M. MitchellMachine Learning is at the forefront of advancements in Artificial Intelligence. It’s moving fast with new research coming out each and every day. This post is in continuation of important concepts and notes right from the basics to advance, from the book Machine Learning, by Tom M. Mitchell.For Machine Learning Notes 1, please click the link below.Machine Learning Notes 1CHAPTER 2: CONCEPT LEARNING AND THE GENERAL-TO-SPECIFIC ORDERING2.1 Concept LearningA problem of searching through a predefined space of potential hypothesis for the hypothesis that best fits the training example.Inferring a boolean-valued function from training examples of its input and output.Inductive Learning HypothesisAny hypothesis found to approximate the target function well (...)
Interview with Deep Learning freelance consultant and #blockchain dev: Mamy André-Ratsimbazafy
▻https://hackernoon.com/interview-with-deep-learning-freelance-consultant-and-blockchain-dev-mam
Part 18 of The series where I interview my heroes.Index to “Interviews with ML Heroes”Today I’m honoured to be talking to one of the great contributors to Kaggle Noobs community: Mamy André-Ratsimbazafy.Mamy is currently working as a Deep Learning freelance consultant and Blockchain dev.In a “previous life”, he has:Passed the CFA level 1 (Chartered Financial Analyst)Worked in financial markets (Société Générale) & private wealth management (J.P. Morgan)Worked at a social startup (Horyou) & a non-profit (Fondation de France)About the Series:I have very recently started making some progress with my Self-Taught Machine Learning Journey. But to be honest, it wouldn’t be possible at all without the amazing community online and the great people that have helped me.In this Series of Blog Posts, I (...)
#mamy-andre-ratsimbazafy #deep-learning #machine-learning #artificial-intelligence
What I learned when trying to improve an AI agent in a game using deep learning
▻https://hackernoon.com/what-i-learned-when-trying-to-improve-an-ai-agent-in-a-game-using-deep-l
Late 2018 I participated in kaggle’s “Quick, Draw! Doodle Recognition Challenge”.For those of you who are unaware, below is a short description of this game:“Quick, Draw!” was released as an experimental game to educate the public in a playful way about how AI works. The game prompts users to draw an image depicting a certain category, such as ”banana,” “table,” etc.As part of this competition, a subset of more than 1B drawings was released which had 340 labels. The competitors needed to improve the existing AI algorithm which distinguishes whether a user has correctly been able to draw what was asked for. For each test image, the need was to predict the three most probable classes the doodle might belong to.key_id,word9000003627287624,The_Eiffel_Tower airplane (...)
#convolutional-network #deep-learning #kaggle-competition #artificial-intelligence #machine-learning
La machine à expulser surchauffe… En 8 jours au moins 100 arrestations sur nos routes migratoires, 50 incarcérations dans nos centres fermés
Entre le 4/01/2019 et le 11/01/2019 (8 jours) au moins 100 migrants ont été arrêtés à #Zeebruges, #Anvers, sur des parkings et dans des camions, dans les trains (même étant porteurs de ticket de voyage) principalement sur la route vers la côte …
50 personnes selon nos chiffres ont été mises en centre fermé . 18 sont depuis libérées grâce à un recours en extrême urgence devant le CCE (conseil du contentieux) contre leur enfermement et/ou leur Ordre de quitter le territoire. D’autres libérations vont suivre.
Le personnel des centres continue à faire le sale boulot de collabo, commandé par leur patron, l’Office des Étrangers.
Les assistant.e.s sociaux continuent à les menacer d’expulsion dès leur arrivée au centre et leur font croire que si iEls prennent un avocat iEls risquent de ne pas être libéré.e.s.
Malheureusement certain.e.s croient ce que l’AS leur dit. Résultat : iEls restent dans le centre sans avocat et sont après quelques semaines expulsé.e.s vers leur pays Dublin, ou pire sont expulsé.e.s vers leur pays d’origine après plusieurs mois de détention.
Ainsi, après 8 mois d’incarcération, une femme et un homme ont déjà subi une expulsion de force et avec escorte ces derniers mois vers l’Éthiopie. La dernière a été expulsée de force ce lundi 07/01/2019. À ce jour (13/01/2019) nous n’avons pas encore de nouvelles de son arrivée à Addis-Abeba !
Plusieurs autres sont menacé·e·s d’expulsion vers l’Éthiopie, pays avec lequel l’Office a trouvé vraisemblablement un accord secret pour faciliter ces expulsions. Une personne a déjà subi 2 tentatives d’expulsion et est dans une état déplorable, la troisième tentative arrivera rapidement. Tenez-vous prêt·e·s ! ▻http://www.gettingthevoiceout.org/comment-arreter-une-expulsion
Il semble que la compagnie ETHIOPIAN AIRLINES est la compagnie qui collabore à ces expulsions.
▻http://www.gettingthevoiceout.org/la-machine-a-expulser-surchauffe-en-8-jours-au-moins-100-arresta
#machine_à_expulsion #Belgique #asile #migrations #réfugiés #renvois #expulsions #rétention #détention_administrative #Ethiopie #réfugiés_éthyopiens
Explaining Machine Learning in Simple Terms
▻https://hackernoon.com/explaining-machine-learning-in-simple-terms-99aadd1b876a?source=rss----3
Today, I would like to talk about machine learning (ML) and put it simply for you. In a nutshell, what exactly machine learning is; how it is applied in practice and what potential it has. I will illustrate the points with simple examples to make it easier to understand.Many people think that machine learning is something about image recognition, but this perception is completely narrow. Machine learning is a whole world that changes industries for the better and affects lives of us all.So, what exactly is machine learning?Machine learning is a data analysis method that identifies patterns and algorithms, learns from them and utilizes for making accurate predictions and better decisions without or with minimal human guidance.The key word here is data. Machine learning learns (we cannot (...)
#machine-learning #ml-explained #data-science #explaining-ml #whats-machine-learning
How To Become Data Scientist Without CS Degree
▻https://hackernoon.com/how-to-become-data-scientist-without-cs-degree-f2b17a79d28b?source=rss--
Last year of the university, quite hard days you might imagine. Every second pass with the anxiety of future when you turned off the screen of any device and moved away from social media or anything else that killing your time. I was in one of these times. Nausea had begun. But it wasn’t a physical sickness as you thought. I’m about nausea of existence that Jean-Paul Sartre describes very well in his books. I felt like I must find a job directly after graduation and I mustn’t delay it because I’m already in my last year. You often feel that kind of moments if you live in a country which struggles with unemployment. I turned on my pc and started searching about departments I can apply for work after graduation. But there were lots of business departments I can apply to. So better to (...)
#machine-learning #data-science #how-to #self #data-scientist
Text Generation for Char LSTM models
▻https://hackernoon.com/text-generation-for-char-lstm-models-685dc186e319?source=rss----3a8144ea
Train a character-level language model on a corpus of jokes.I decided to experiment with approaches to this problem, which I found on #openai’s Request for Research blog. You can have a look at the code here. This is written in Pytorch, and is heavily inspired by Fast.ai’s fantastic lesson on implementing RNN’s from scratch.Data preparation I started off using the dataset provided by OpenAI. The data was converted to lowercase and for an initial run, I selected the top rated jokes, with a word length of less than 200. Here’s an example of all the tokens encountered:Explicit words ahead! This particular dataset has explicit words/content, so those come up in the output predictions of the model. Another interesting problem to work on would be to filter out inappropriate words from the output (...)
#programming #machine-learning #artificial-intelligence #python
Text summarizer using deep learning made easy
▻https://hackernoon.com/text-summarizer-using-deep-learning-made-easy-490880df6cd?source=rss----
In this series we will discuss a truly exciting natural language processing topic that is using deep learning techniques to summarize text , the code for this series is open source , and is found in a jupyter notebook format , to allow it to run on google colab without the need to have a powerful gpu , in addition all data is open source , and you don’t have to download it , as you can connect google colab with google drive and put your data directly onto google drive , without the need to download it locally , read this blog to learn more about google colab with google drive .To summarize text you have 2 main approaches (i truly like how it is explained in this blog)Extractive method , which is choosing specific main words from the input to generate the output , this model tends to work , but (...)
#machine-learning #seq2seq #text-summarization #artificial-intelligence #ai
Make an Eye tracking and Face detection app as a beginner
▻https://hackernoon.com/make-an-eye-tracking-and-face-detection-app-as-a-beginner-d72e0139546b?s
We all know, how cool an #android app looks, when it can detect our face or track if our eyes are closed or open. It becomes way more cooler when the app can even detect if we are smiling, reading on phone or not looking at it.Well…I believe.. whatever does appeals me, simply makes me build it!Sorry, tried a “The Dark Knight” pun :)So let us make an android eye tracking and face detection app using Google Vision API.From Google:Cloud Vision API enables developers to understand the content of an image by encapsulating powerful machine learning models in an easy-to-use REST API. It quickly classifies images into thousands of categories (such as, “sailboat”), detects individual objects and faces within images, and reads printed words contained within images. You can build metadata on your image (...)
#python Pandas — Basics to Beyond
▻https://hackernoon.com/python-pandas-tutorial-92018da85a33?source=rss----3a8144eabfe3---4
Python Pandas — Basics to BeyondA tutorial walkthrough of Python Pandas LibraryFor those of you who are getting started with Machine learning, just like me, would have come across Pandas, the data analytics library. In the rush to understand the gimmicks of ML, we often fail to notice the importance of this library. But soon you will hit a roadblock where you would need to play with your data, clean and perform data transformations before feeding it into your ML model.Why do we need this blog when there are already a lot of documentation and tutorials? Pandas, unlike most python libraries, has a steep learning curve. The reason is that you need to understand your data well in order to apply the functions appropriately. Learning Pandas syntactically is not going to get you anywhere. Another (...)
#data-visualization #machine-learning #python-pandas #data-science
Implementing a Sequence-to-Sequence Model
▻https://hackernoon.com/implementing-a-sequence-to-sequence-model-45a6133958ca?source=rss----3a8
Learn how to implement a sequence-to-sequence model in this article by Matthew Lamons, founder, and CEO of Skejul — the AI platform to help people manage their activities, and Rahul Kumar, an AI scientist, deep learning practitioner, and independent researcher.In this article, you’ll implement a seq2seq model (an encoder-decoder RNN) for a simple sequence-to-sequence question-answer task. This model can be trained to map an input sequence (questions) to an output sequence (answers), which are not necessarily of the same length as each other.This type of seq2seq model has shown impressive performance in various other tasks such as speech recognition, machine translation, question answering, Neural Machine Translation (NMT), and image caption generation.The following diagram helps you (...)
Logistic Regression with #tensorflow and #keras
▻https://hackernoon.com/logistic-regression-with-tensorflow-and-keras-83d2487aed89?source=rss---
Learn logistic regression with TensorFlow and Keras in this article by Armando Fandango, an inventor of AI empowered products by leveraging expertise in deep learning, machine learning, distributed computing, and computational methods. He has also provided thought leadership roles as Chief Data Scientist and Director at startups and large enterprises.This article will show you how to implement a classification algorithm, known as multinomial logistic regression, to identify the handwritten digits #dataset. You’ll use both TensorFlow core and Keras to implement this logistic regression algorithm.Logistic regression with TensorFlowOne of the most popular examples regarding multiclass classification is to label the images of handwritten digits. The classes, or labels, in this example are (...)
ResNet: Block Level Design with Deep Learning Studio |PART 1|
▻https://hackernoon.com/resnet-block-level-design-with-deep-learning-studio-part-1-727c6f4927ac?
1 — The problem of very deep neural networksThe main benefit of a very deep network is that it can represent very complex functions. It can also learn features at many different levels of abstraction, from edges (at the lower layers) to very complex features (at the deeper layers). However, using a deeper network doesn’t always help. A huge barrier to training them is vanishing gradients: very deep networks often have a gradient signal that goes to zero quickly, thus making gradient descent unbearably slow. More specifically, during gradient descent, as you backprop from the final layer back to the first layer, you are multiplying by the weight matrix on each step, and thus the gradient can decrease exponentially quickly to zero (or, in rare cases, grow exponentially quickly and “explode” (...)
#deep-learning #artificial-intelligence #machine-learning #neural-networks #block-level-design
Joel Simon - Dimensions of dialogue
▻http://joelsimon.net/dimensions-of-dialogue.html
Here, new writing systems are created by challenging two neural networks to communicate information via images. Using the magic of machine learning, the networks attempt to create their own emergent language isolate that is robust to noise.
Uni-Variate, Polynomial and Multi-Variate Regression using OLS/Normal Equation Approach (A-Z)
▻https://hackernoon.com/uni-variate-polynomial-and-multi-variate-regression-using-ols-normal-equ
Learn, Code and Tune…As I mentioned in my previous article:Implementation of Uni-Variate Linear Regression in Python using Gradient Descent Optimization from…apart from Gradient Descent Optimization, there is another approach known as Ordinary Least Squares or Normal Equation Method. This approach, by far is the most successful and adopted in many Machine Learning Toolboxes. There is a descriptive reason behind OLS/Normal Equation Method being successful and widely preferred for Gradient Descent, to which I will be coming in the latter half of this article. Firstly, let’s move on to the Approach and its Python Implementation, secondly, applying it on Practice Datasets and finally, describing intuitively that why this over-performs Gradient Descent.The Ordinary Least Squares approach for (...)
#data-science #data-visualization #machine-learning #calculus #python3
Interview. How Neural Networks And Machine Learning Are Making #games More Interesting
▻https://hackernoon.com/interview-how-neural-networks-and-machine-learning-are-making-games-more
[Interview] How Neural Networks And Machine Learning Are Making Games More InterestingImage credit: UnsplashMachine learning and neural networks are hot topics in many tech areas, and the game dev is one of them. There such new technologies are used to make games more interesting.How this is achieved, what companies are now leaders in new tech adoption and research when we as users will see any notable results of this research and lots more to be discussed today. We will talk to Vladimir Ivanov, the leading ML in gaming expert.The first question is: what do you mean when talking that games are “not interesting” and the new tech could fix this?Well, the thing is pretty simple: if we are talking not about human vs. human game mode, you need to compete with bots. Often this is not that (...)
#gamedev #machine-learning #game-development #artificial-intelligence
Design Fair Markets by Using Algorithms
▻https://hackernoon.com/design-fair-markets-by-using-algorithms-6660e49241a9?source=rss----3a814
Machine learning should fuel an inclusive societyFoto credit: City of GreeleyFairness and bias in machine learning is a blossoming line of research. Most of this work focuses on discrimination and inclusion. While this is an important line of research that I wholeheartedly support, I propose tech companies and platforms would also start working on “biased” algorithms that facilitate fair markets.In this post I will argue that:Bias and unfairness are pervasive in tech including machine learningFairness of markets can also be facilitated by machine learningUnfairness is pervasive in techTry it out: type “He is a nurse. She is a doctor.” into Google Translate and translate it into Turkish. Then translate the result (“O bir bebek hemşire. O bir doktor.”) into English and you get “She is a nurse. He (...)
#fair-markets-algorithm #market-design #ai #machine-learning #design-fair-markets