GMM-UBM и алгоритма MAP adaptation https://habr.com/post/420515/
Habr
Диаризация на основе модели GMM-UBM и алгоритма MAP adaptation
Привет, Хабр. Я бы хотел рассказать об одном из подходов в решении задачи диаризации дикторов и показать, как этот метод можно реализовать на языке python. Чтобы не отпугивать читателя, я не буду...
Introducing the Unrestricted Adversarial Examples Challenge https://ai.googleblog.com/2018/09/introducing-unrestricted-adversarial.html
blog.research.google
Introducing the Unrestricted Adversarial Examples Challenge
How to Model Human Activity From Smartphone Data https://machinelearningmastery.com/how-to-model-human-activity-from-smartphone-data/
MachineLearningMastery.com
How to Model Human Activity From Smartphone Data - MachineLearningMastery.com
Human activity recognition is the problem of classifying sequences of accelerometer data recorded by specialized harnesses or smart phones into known well-defined movements. It is a challenging problem given the large number of observations produced each…
A new understanding of Batch Normalization https://medium.com/@geetankr/a-new-understanding-of-batch-normalization-e11e05e120dc
Medium
A new understanding of Batch Normalization
Batch Normalization(BN) was introduced by [1] back in 2015. Since then it has been used in the most deep learning models to improve…
Machine Learning Crash Course
with TensorFlow APIs https://developers.google.com/machine-learning/crash-course/
with TensorFlow APIs https://developers.google.com/machine-learning/crash-course/
Google for Developers
Machine Learning | Google for Developers
deep learning object detection
A paper list of object detection using deep learning.
https://github.com/hoya012/deep_learning_object_detection
A paper list of object detection using deep learning.
https://github.com/hoya012/deep_learning_object_detection
GitHub
GitHub - hoya012/deep_learning_object_detection: A paper list of object detection using deep learning.
A paper list of object detection using deep learning. - hoya012/deep_learning_object_detection
How to Develop 1D Convolutional Neural Network Models for Human Activity Recognition https://machinelearningmastery.com/cnn-models-for-human-activity-recognition-time-series-classification/
Geoffrey Hinton: The Foundations of Deep Learning https://www.youtube.com/watch?v=zl99IZvW7rE
YouTube
Geoffrey Hinton: The Foundations of Deep Learning
Godfather of artificial intelligence Geoffrey Hinton gives an overview of the foundations of deep learning. In this talk, Hinton breaks down the advances of neural networks, as applied to speech and object recognition, image segmentation and reading or generating…
Forwarded from Python/ django
Two Sigma: Using News to Predict Stock Movements
Use news analytics to predict stock price performance
1st place - $25,000
2nd place - $20,000
3rd place - $15,000
4th through 7th place - $10,000 each
This is a two-stage competition consisting of a Submission period and a Scoring period. In the Submission period, entrants will train their models in Kaggle Kernels. During the Scoring period, models submitted at the end of the submission period will be evaluated against regularly updated news and market data.
Start Date: 9/25/2018
Rules Acceptance/Team Merger Deadline: 1/2/2019
Submission Deadline: 1/8/2019 After this date, we will not be taking any more submissions. You can sit back and watch the leaderboard unfold. Remember to select your two best submissions to be rescored. In this competition we will not auto-select your two submissions.
End Date: 7/15/2019
https://www.kaggle.com/c/two-sigma-financial-news
Use news analytics to predict stock price performance
1st place - $25,000
2nd place - $20,000
3rd place - $15,000
4th through 7th place - $10,000 each
This is a two-stage competition consisting of a Submission period and a Scoring period. In the Submission period, entrants will train their models in Kaggle Kernels. During the Scoring period, models submitted at the end of the submission period will be evaluated against regularly updated news and market data.
Start Date: 9/25/2018
Rules Acceptance/Team Merger Deadline: 1/2/2019
Submission Deadline: 1/8/2019 After this date, we will not be taking any more submissions. You can sit back and watch the leaderboard unfold. Remember to select your two best submissions to be rescored. In this competition we will not auto-select your two submissions.
End Date: 7/15/2019
https://www.kaggle.com/c/two-sigma-financial-news
Kaggle
Two Sigma: Using News to Predict Stock Movements
Use news analytics to predict stock price performance
Brilliant post on #CS and #Software about strategy and psychology of Software Development, which is highly applicable to Data Science too.
“Imaginary Problems Are the Root of Bad Software”
https://medium.com/s/story/imaginary-problems-d4f2921bd1b8
“Imaginary Problems Are the Root of Bad Software”
https://medium.com/s/story/imaginary-problems-d4f2921bd1b8
Medium
Imaginary Problems Are the Root of Bad Software
Just because they're fun to solve doesn't mean they're relevant
Необычные материалы в робототехнике.
У каждого робота должен быть блестящий металлический зад, это знают все. Но в реальных роботах металла не так уж и много — с ним соседствуют пластики, композиты и силикон, а порой и совсем нестандартные субстанции: http://amp.gs/hCG8
У каждого робота должен быть блестящий металлический зад, это знают все. Но в реальных роботах металла не так уж и много — с ним соседствуют пластики, композиты и силикон, а порой и совсем нестандартные субстанции: http://amp.gs/hCG8
Comparison of top data science libraries for Python, R and Scala [Infographic]
https://medium.com/activewizards-machine-learning-company/comparison-of-top-data-science-libraries-for-python-r-and-scala-infographic-574069949267
https://medium.com/activewizards-machine-learning-company/comparison-of-top-data-science-libraries-for-python-r-and-scala-infographic-574069949267
Medium
Comparison of top data science libraries for Python, R and Scala [Infographic]
Data science is a promising and exciting field, developing rapidly. The area of data science use cases and influence is continuously…