Pytorch implementation of Grad-CAM
https://github.com/jacobgil/pytorch-grad-cam
https://github.com/jacobgil/pytorch-grad-cam
GitHub
GitHub - jacobgil/pytorch-grad-cam: Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification…
Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more. - jacobgil/pytorch-grad-cam
Visualizing TensorFlow Graphs in Jupyter Notebooks
https://blog.jakuba.net/2017/05/30/tensorflow-visualization.html
https://blog.jakuba.net/2017/05/30/tensorflow-visualization.html
blog.jakuba.net
Visualizing TensorFlow Graphs in Jupyter Notebooks
Prerequisites: This article assumes you are familiar with the basics of Python, TensorFlow, and Jupyter notebooks. We won't use any of the advanced TensorFlo...
A deep dive into what AI actually means in 2017
https://blog.statsbot.co/3-types-of-artificial-intelligence-4fb7df20fdd8
https://blog.statsbot.co/3-types-of-artificial-intelligence-4fb7df20fdd8
Stats and Bots
A Big Data Cheat Sheet: From Narrow AI to General AI
Artificial Intelligence in 2017
Как научиться науке о данных (Data Science). И при этом не заплатив 150,000 рублей
http://spark-in.me/post/learn-data-science
http://spark-in.me/post/learn-data-science
From Instance Noise to Gradient Regularisation
http://www.inference.vc/from-instance-noise-to-gradient-regularisation/
http://www.inference.vc/from-instance-noise-to-gradient-regularisation/
inFERENCe
From Instance Noise to Gradient Regularisation
This is just a short note to highlight a new paper I read recently: Roth, Lucchi, Nowozin and Hofmann (2017) Stabilizing Training of Generative Adversarial Networks through Regularization Instance noise Last year, we and Arjovsky & Buttou (2017) independently…
spaCy's Machine Learning library for NLP in Python
https://github.com/explosion/thinc
https://github.com/explosion/thinc
GitHub
GitHub - explosion/thinc: 🔮 A refreshing functional take on deep learning, compatible with your favorite libraries
🔮 A refreshing functional take on deep learning, compatible with your favorite libraries - explosion/thinc
PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation
https://github.com/jacobgil/pytorch-explain-black-box
https://github.com/jacobgil/pytorch-explain-black-box
GitHub
jacobgil/pytorch-explain-black-box
PyTorch implementation of Interpretable Explanations of Black Boxes by Meaningful Perturbation - jacobgil/pytorch-explain-black-box
You can probably use deep learning even if your data isn't that big
http://beamandrew.github.io/deeplearning/2017/06/04/deep_learning_works.html
http://beamandrew.github.io/deeplearning/2017/06/04/deep_learning_works.html
WebDNN: JS Library to run DL models in browser. Optimized WebASM+GPU implementation.
https://mil-tokyo.github.io/webdnn/
https://mil-tokyo.github.io/webdnn/
mil-tokyo.github.io
MIL WebDNN
WebDNN is an open source software framework for fast execution of deep neural network (DNN) pre-trained model on web browser.
Visualizing the Latent Space of Vector Drawings from the Google QuickDraw Dataset with SketchRNN, PCA and t-SNE
http://louistiao.me/posts/notebooks/visualizing-the-latent-space-of-vector-drawings-from-the-google-quickdraw-dataset-with-sketchrnn-pca-and-t-sne/
http://louistiao.me/posts/notebooks/visualizing-the-latent-space-of-vector-drawings-from-the-google-quickdraw-dataset-with-sketchrnn-pca-and-t-sne/
"in the brain, such a representation is produced by an architecture similar to a hierarchical feedforward deep-network"
http://www.cell.com/cell/abstract/S0092-8674(17)30538-X
http://www.cell.com/cell/abstract/S0092-8674(17)30538-X
Бесплатный 3-месячный курс по глубокому обучению от Google https://www.udacity.com/course/deep-learning--ud730
Машинное обучение и анализ данных: решаем практические задачи с победителями индустриального хакатона ЛК
https://habrahabr.ru/company/kaspersky/blog/330282/
https://habrahabr.ru/company/kaspersky/blog/330282/
habrahabr.ru
Машинное обучение и анализ данных: решаем практические задачи с победителями индустриального хакатона ЛК
Как вычислить замыслы киберпреступников, атакующих промышленный объект и распознать слабые сигналы SOS, которые периодически подает индустриальная АСУ ТП на...
Tensorflow I Love You, But You're Bringing Me Down
http://blog.nateharada.com/tensorflow-i-love-you-but
http://blog.nateharada.com/tensorflow-i-love-you-but
40+ приложений технологии машинного обучения для бизнеса
https://habrahabr.ru/post/324694/
https://habrahabr.ru/post/324694/
habrahabr.ru
40+ приложений технологии машинного обучения для бизнеса
Перевод поста Филиппа Ходжетта, выступавшего недавно на конференции Hollywood Professional Association Tech Retreat. Надеюсь, собранный в одном месте список...
Эволюционные стратегии как масштабируемая альтернатива обучению с подкреплением
https://habrahabr.ru/post/330342/
https://habrahabr.ru/post/330342/
habrahabr.ru
Эволюционные стратегии как масштабируемая альтернатива обучению с подкреплением
Изложение статьи от том, что давно известные эволюционные стратегии оптимизации могут превзойти алгоритмы обучения с подкреплением. Преимущества эволюционных...
The 5 Step Life-Cycle for Long Short-Term Memory Models in Keras
http://machinelearningmastery.com/5-step-life-cycle-long-short-term-memory-models-keras/
http://machinelearningmastery.com/5-step-life-cycle-long-short-term-memory-models-keras/
MachineLearningMastery.com
The 5 Step Life-Cycle for Long Short-Term Memory Models in Keras - MachineLearningMastery.com
Deep learning neural networks are very easy to create and evaluate in Python with Keras, but you must follow a strict model life-cycle.
In this post, you will discover the step-by-step life-cycle for creating, training, and evaluating Long Short-Term Memory…
In this post, you will discover the step-by-step life-cycle for creating, training, and evaluating Long Short-Term Memory…