Fraud detection with cost-sensitive machine learning
🔗 Fraud detection with cost-sensitive machine learning
The concept of example-dependent cost-sensitive classification algorithms
🔗 Fraud detection with cost-sensitive machine learning
The concept of example-dependent cost-sensitive classification algorithms
Towards Data Science
Fraud detection with cost-sensitive machine learning
The concept of example-dependent cost-sensitive classification algorithms
🎥 Beautiful Gooey Simulations, Now 10 Times Faster
👁 2 раз ⏳ 187 сек.
👁 2 раз ⏳ 187 сек.
❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers
📝 The paper "GPU Optimization of Material Point Methods" is available here:
http://www.cemyuksel.com/research/papers/gpu_mpm.pdf
🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
313V, Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bruno Brito, Christian Ahlin, Christoph Jadanowski, Claudio Fernandes, Dennis Abts, Eric Haddad, Eric Martel, EvaVk
Beautiful Gooey Simulations, Now 10 Times Faster
❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers
📝 The paper "GPU Optimization of Material Point Methods" is available here:
http://www.cemyuksel.com/research/papers/gpu_mpm.pdf
🙏 We would like to thank our generous Patreon…
📝 The paper "GPU Optimization of Material Point Methods" is available here:
http://www.cemyuksel.com/research/papers/gpu_mpm.pdf
🙏 We would like to thank our generous Patreon…
https://www.youtube.com/playlist?list=PLoROMvodv4rOABXSygHTsbvUz4G_YQhOb
lfd
🔗 CS230: Deep Learning | Autumn 2018 - YouTube
lfd
🔗 CS230: Deep Learning | Autumn 2018 - YouTube
YouTube
Stanford CS230: Deep Learning | Autumn 2018
Lectures from Stanford graduate course CS230 taught by Andrew Ng. You will learn about Convolutional networks, RNNs, LSTM, Adam, Dropout, BatchNorm, Xavier/H...
Build XGBoost / LightGBM models on large datasets — what are the possible solutions?
🔗 Build XGBoost / LightGBM models on large datasets — what are the possible solutions?
XGBoost and LightGBM have been proven on many tabular datasets to be the best performant ML algorithms. But when the data is huge, how do…
🔗 Build XGBoost / LightGBM models on large datasets — what are the possible solutions?
XGBoost and LightGBM have been proven on many tabular datasets to be the best performant ML algorithms. But when the data is huge, how do…
Towards Data Science
Build XGBoost / LightGBM models on large datasets — what are the possible solutions?
XGBoost and LightGBM have been proven on many tabular datasets to be the best performant ML algorithms. But when the data is huge, how do…
https://www.climatechange.ai
🔗 Climate change: How can AI help?
Applying machine learning to address the problems of climate change
🔗 Climate change: How can AI help?
Applying machine learning to address the problems of climate change
Только начали изучать машинное обучение и компьютерное зрение или уже давно знакомы с этой сферой? В любом случае заходи к нам . У нас есть материал как для новичков, так и для специалистов. Также у нас много интересной информации для тех, кто хочет лишь следить за развитием технологий в данной сфере.
Заинтересовался?Поддержи подпиской!
Заинтересовался?Поддержи подпиской!
🎥 Deep Learning: Miracle or Snake Oil?
👁 1 раз ⏳ 3126 сек.
👁 1 раз ⏳ 3126 сек.
The latest craze are deep neural networks. How does deep learning work and are neural networks a modern miracle or yet another false dawn?
A lecture by Richard Harvey, IT Livery Company Professor of IT 19 March 2019
https://www.gresham.ac.uk/lectures-and-events/deep-learning
Machine Learning has had several excitements over the years with machines that are modelled on the human brain. The invention of the perceptron and artificial neural networks were followed by intense scientific activity and excitemenVk
Deep Learning: Miracle or Snake Oil?
The latest craze are deep neural networks. How does deep learning work and are neural networks a modern miracle or yet another false dawn?
A lecture by Richard Harvey, IT Livery Company Professor of IT 19 March 2019
https://www.gresham.ac.uk/lectures-and…
A lecture by Richard Harvey, IT Livery Company Professor of IT 19 March 2019
https://www.gresham.ac.uk/lectures-and…
Graduating in GANs: Going from understanding generative adversarial networks to running your own
🔗 Graduating in GANs: Going from understanding generative adversarial networks to running your own
Read how generative adversarial networks (GANs) research and evaluation has developed then implement your own GAN to generate handwritten
🔗 Graduating in GANs: Going from understanding generative adversarial networks to running your own
Read how generative adversarial networks (GANs) research and evaluation has developed then implement your own GAN to generate handwritten
Towards Data Science
Graduating in GANs: Going from understanding generative adversarial networks to running your own
Read how generative adversarial networks (GANs) research and evaluation has developed then implement your own GAN to generate handwritten
Who Will Win the Game of Thrones?
🔗 Who Will Win the Game of Thrones?
The final season of Game of Thrones is finally here and the question on everyone’s mind is: Who will end up on the Iron Throne?
🔗 Who Will Win the Game of Thrones?
The final season of Game of Thrones is finally here and the question on everyone’s mind is: Who will end up on the Iron Throne?
Towards Data Science
Who Will Win the Game of Thrones?
The final season of Game of Thrones is finally here and the question on everyone’s mind is: Who will end up on the Iron Throne?
Normalization vs Standardization — Quantitative analysis
🔗 Normalization vs Standardization — Quantitative analysis
Stop using StandardScaler from Sklearn as a default feature scaling method can get you a boost of 7% in accuracy!
🔗 Normalization vs Standardization — Quantitative analysis
Stop using StandardScaler from Sklearn as a default feature scaling method can get you a boost of 7% in accuracy!
Towards Data Science
Normalization vs Standardization — Quantitative analysis
Stop using StandardScaler from Sklearn as a default feature scaling method can get you a boost of 7% in accuracy!
МегаФон 💚💚💜 (резюме в личку)
https://hh.ru/vacancy/30374086
https://hh.ru/vacancy/30373162
🔗 Вакансия Главный аналитик SQL в Москве, работа в МегаФон
Вакансия Главный аналитик SQL. Зарплата: не указана. Москва. Требуемый опыт: 3–6 лет. Полная занятость. Дата публикации: 25.03.2019.
https://hh.ru/vacancy/30374086
https://hh.ru/vacancy/30373162
🔗 Вакансия Главный аналитик SQL в Москве, работа в МегаФон
Вакансия Главный аналитик SQL. Зарплата: не указана. Москва. Требуемый опыт: 3–6 лет. Полная занятость. Дата публикации: 25.03.2019.
hh.ru
Вакансия Главный аналитик SQL в Москве, работа в компании МегаФон (вакансия в архиве)
Зарплата: не указана. Москва. Требуемый опыт: 3–6 лет. Полная занятость. Дата публикации: 24.04.2019.
🎥 Занятие 5 | Машинное обучение
👁 3 раз ⏳ 3473 сек.
👁 3 раз ⏳ 3473 сек.
Преподаватель: Власов Кирилл Вячеславович
Материалы курса: https://github.com/ml-dafe/ml_mipt_dafe_minor
Дата: 30.03.2019Vk
Занятие 5 | Машинное обучение
Преподаватель: Власов Кирилл Вячеславович
Материалы курса: https://github.com/ml-dafe/ml_mipt_dafe_minor
Дата: 30.03.2019
Материалы курса: https://github.com/ml-dafe/ml_mipt_dafe_minor
Дата: 30.03.2019
Beyond A/B Testing: Multi-armed Bandit Experiments
🔗 Beyond A/B Testing: Multi-armed Bandit Experiments
An implementation of Google Analytics’ stochastic k-armed bandit test with Thompson sampling and Monte Carlo simulation
🔗 Beyond A/B Testing: Multi-armed Bandit Experiments
An implementation of Google Analytics’ stochastic k-armed bandit test with Thompson sampling and Monte Carlo simulation
Towards Data Science
Beyond A/B Testing: Multi-armed Bandit Experiments
An implementation of Google Analytics’ stochastic k-armed bandit test with Thompson sampling and Monte Carlo simulation
A Gentle Introduction to Channels First and Channels Last Image Formats for Deep Learning
🔗 A Gentle Introduction to Channels First and Channels Last Image Formats for Deep Learning
Color images have height, width, and color channel dimensions. When represented as three-dimensional arrays, the channel dimension for the image data is last by default, but may be moved to be the first dimension, often for performance-tuning reasons. The use of these two “channel ordering formats” and preparing data to meet a specific preferred channel …
🔗 A Gentle Introduction to Channels First and Channels Last Image Formats for Deep Learning
Color images have height, width, and color channel dimensions. When represented as three-dimensional arrays, the channel dimension for the image data is last by default, but may be moved to be the first dimension, often for performance-tuning reasons. The use of these two “channel ordering formats” and preparing data to meet a specific preferred channel …
Generative model of fonts as SVG instead of pixels. Structured format enables flexible manipulation arxiv.org/abs/1904.02632
🔗 A Learned Representation for Scalable Vector Graphics
Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world. In spite of such advances, a higher level understanding of vision and imagery does not arise from exhaustively modeling an object, but instead identifying higher-level attributes that best summarize the aspects of an object. In this work we attempt to model the drawing process of fonts by building sequential generative models of vector graphics. This model has the benefit of providing a scale-invariant representation for imagery whose latent representation may be systematically manipulated and exploited to perform style propagation. We demonstrate these results on a large dataset of fonts and highlight how such a model captures the statistical dependencies and richness of this dataset. We envision that our model can find use as a tool for graphic designers to facilitate font design.
🔗 A Learned Representation for Scalable Vector Graphics
Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world. In spite of such advances, a higher level understanding of vision and imagery does not arise from exhaustively modeling an object, but instead identifying higher-level attributes that best summarize the aspects of an object. In this work we attempt to model the drawing process of fonts by building sequential generative models of vector graphics. This model has the benefit of providing a scale-invariant representation for imagery whose latent representation may be systematically manipulated and exploited to perform style propagation. We demonstrate these results on a large dataset of fonts and highlight how such a model captures the statistical dependencies and richness of this dataset. We envision that our model can find use as a tool for graphic designers to facilitate font design.
arXiv.org
A Learned Representation for Scalable Vector Graphics
Dramatic advances in generative models have resulted in near photographic quality for artificially rendered faces, animals and other objects in the natural world. In spite of such advances, a...
Data Science Essentials in Python — Dmitry Zinoviev (en) 2916
📝 2_5447441436813296252.pdf - 💾10 881 637
📝 2_5447441436813296252.pdf - 💾10 881 637
The Data Fabric for Machine Learning. Part 2: Building a Knowledge-Graph.
🔗 The Data Fabric for Machine Learning. Part 2: Building a Knowledge-Graph.
Before being able to develop a Data Fabric we need to build a Knowledge-Graph. In this article I’ll set up the basis on how to create it…
🔗 The Data Fabric for Machine Learning. Part 2: Building a Knowledge-Graph.
Before being able to develop a Data Fabric we need to build a Knowledge-Graph. In this article I’ll set up the basis on how to create it…
Towards Data Science
The Data Fabric for Machine Learning. Part 2: Building a Knowledge-Graph.
Before being able to develop a Data Fabric we need to build a Knowledge-Graph. In this article I’ll set up the basis on how to create it…