🎥 Tutorial 2019 || Cryptocurrency-predicting RNN intro - Deep Learning w/ Python, TensorFlow and Keras
👁 1 раз ⏳ 1234 сек.
Tutorial 2019 || Cryptocurrency-predicting RNN intro - Deep Learning w/ Python, TensorFlow and Keras p.8

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://towardsdatascience.com/the-relationship-between-biological-and-artificial-intelligence-aeaf5fb93e19?source=collection_home---4------1---------------------

🔗 The relationship between Biological and Artificial Intelligence
Critical review of the claims of brain/neuroscience inspiration in AI, especially Artificial Neural Networks

​PyTorch 1.1
https://github.com/pytorch/pytorch/releases/tag/v1.1.0

- Tensorboard (beta);
- DistributedDataParallel new functionality and tutorials;
- Multi-headed attention;
- EmbeddingBag enhancements;
- Other cool, but more niche features:
- nn.SyncBatchNorm;
- optim.lr_scheduler.CyclicLR;

🔗 pytorch/pytorch
Tensors and Dynamic neural networks in Python with strong GPU acceleration - pytorch/pytorch

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

🔗 If you like to travel, let Python help you scrape the best fares!
A simple and customizable project with Python and Selenium, that will search for flights and send the prices directly to your email!

​Perelman School of Medicine at the University of Pennsylvania
https://www.med.upenn.edu/urbslab/videos.html

🔗 Videos/Lectures | Urbanowicz Lab | Perelman School of Medicine at the University of Pennsylvania
Welcome to the URBS Lab (Unbounded Research in Biomedical Systems). Our primary goal is to develop, evaluate, and apply tools/strategies that can be leveraged to improve our understanding of human health and the strategies implemented to prevent, diagnose, and treat. This site aims to orient visitors to our past, present, and future research/goals as well as offer relevant resources and links.

Открытый курс OpenDataScience и Mail. ru Group по машинному обучению

1. Pandas
2. Визуализация
3. Классификация, деревья решений
4. Логистическая регрессия
5. Случайный лес
6. Регрессия, работа с признаками

🎥 Лекция 1. Pandas. Открытый курс OpenDataScience по машинному обучению
👁 2900 раз ⏳ 7042 сек.
For lectures in English, check out this playlist https://bit.ly/2zY6Xe2

То же видео, но с улучшенным звуком https://youtu.be/OAy96yiWohk (Denis Ce...

🎥 Лекция 2. Визуализация. Открытый курс OpenDataScience по машинному обучению
👁 623 раз ⏳ 7625 сек.
То же видео, но с улучшенным звуком https://www.youtube.com/watch?v=uwQat1TV0JM (tnx to Denis Cera, Oleg Butko)

На 2-ой лекции мы попрактикуемся в...

🎥 Untitled
👁 12 раз ⏳ 0 сек.


🎥 Untitled
👁 2 раз ⏳ 0 сек.


🎥 Лекция 5. Случайный лес. Открытый курс OpenDataScience по машинному обучению
👁 305 раз ⏳ 8595 сек.
То же видео, но с улучшенным звуком https://youtu.be/_XKQY62NJus (tnx to Denis Cera, Oleg Butko)

На 5-ой лекции обсудим любопытнейший вопрос – поч...

🎥 Лекция 6. Регрессия, регуляризация. Открытый курс OpenDataScience по машинному обучению
👁 255 раз ⏳ 9833 сек.
То же видео, но с улучшенным звуком https://youtu.be/70WsnE4ep1Y (tnx to Denis Cera)

На 6-ой лекции обсудим задачу восстановления регрессии, как ...

​Spectral Inference Networks
https://arxiv.org/abs/1806.02215
http://github.com/deepmind/spectral_inference_networks

🔗 Spectral Inference Networks: Unifying Deep and Spectral Learning
We present Spectral Inference Networks, a framework for learning eigenfunctions of linear operators by stochastic optimization. Spectral Inference Networks generalize Slow Feature Analysis to generic symmetric operators, and are closely related to Variational Monte Carlo methods from computational physics. As such, they can be a powerful tool for unsupervised representation learning from video or graph-structured data. We cast training Spectral Inference Networks as a bilevel optimization problem, which allows for online learning of multiple eigenfunctions. We show results of training Spectral Inference Networks on problems in quantum mechanics and feature learning for videos on synthetic datasets. Our results demonstrate that Spectral Inference Networks accurately recover eigenfunctions of linear operators and can discover interpretable representations from video in a fully unsupervised manner.

​Роман Логинов: Мультимоделирование как универсальный способ описания выборки общего вида

🔗 Роман Логинов: Мультимоделирование как универсальный способ описания выборки общего вида
В случае неоднородных данных в машинном обучении использования одной модели недостаточно. Для выявления этого используют комбинации нескольких моделей - муль...

​https://m.youtube.com/watch?v=FDzIafdbTVw

🔗

​Policy Intelligence: Applying Machine Learning and Analytics to Security in GCP (Cloud Next '19)

🔗 Policy Intelligence: Applying Machine Learning and Analytics to Security in GCP (Cloud Next '19)
Cloud environments today are complex. Even when all the information is available, it’s hard to pull it all together to make a good decision. Imagine if your ...

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data

https://towardsdatascience.com/careful-looking-at-your-model-results-too-much-can-cause-information-leakage-95b4517404bc?source=collection_home---4------4---------------------

🔗 Careful! Looking at Your Model Results Too Much Can Cause Information Leakage
It’s always to use as much data as you can when building machine learning models. I think we all are aware of the issue of overfitting…

​Make your own Super Pandas using Multiproc

🔗 Make your own Super Pandas using Multiproc
Increase your data preprocessing speed using parallelization in Pandas

​Наш телеграм канал - tglink.me/ai_machinelearning_big_data
https://machinelearningmastery.com/best-practices-for-preparing-and-augmenting-image-data-for-convolutional-neural-networks/

🔗 Best Practices for Preparing and Augmenting Image Data for Convolutional Neural Networks
It is challenging to know how to best prepare image data when training a convolutional neural network. This involves both scaling the pixel values and use of augmentation techniques during both the training and evaluation of the model. Instead of testing a wide range of options, a useful shortcut is to consider the types of …

🎥 Python Neural Networks - TensorFlow 2.0 Tutorial - What is a Neural Network?
👁 1 раз ⏳ 1629 сек.
This python neural network tutorial series will discuss how to use tensorflow 2.0 and provide tutorials on how to create neural networks with python and tensorflow. This specific video is the introduction video in the series and discusses what a neural network is.

Want a sneak peak into my life? Follow my Instagram @tech_with_tim where I'm going to be filming a video each morning sharing my goals for the day and what I have planned:
https://www.instagram.com/tech_with_tim

*********************************

​Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & Retrieval
http://ai.googleblog.com/2019/05/announcing-google-landmarks-v2-improved.html/

🔗 Announcing Google-Landmarks-v2: An Improved Dataset for Landmark Recognition & Retrieval
Posted by Bingyi Cao and Tobias Weyand, Software Engineers, Google AI Last year we released Google-Landmarks , the largest world-wide la...

​Using What-If Tool to investigate Machine Learning models.

🔗 Using What-If Tool to investigate Machine Learning models.
An open source tool from Google to easily analyze ML models without the need to code.

​Joining Data Sources

🔗 Joining Data Sources
a must-have skill for data science

​Reinforcement Learning for Real-World Robotics

🔗 Reinforcement Learning for Real-World Robotics
Ideas from the literature on RL for real-world robot control

​A library for real-time video stream decoding to CUDA memory

By Constanta: https://github.com/Fonbet/argus-tensor-stream

🔗 Fonbet/argus-tensor-stream
A library for real-time video stream decoding to CUDA memory - Fonbet/argus-tensor-stream

🎥 Deep Learning with PyTorch - Intermediate Workshop
👁 4 раз ⏳ 10562 сек.
https://www.meetup.com/dsnet-blr/events/260996023/

Code:
- https://jvn.io/aakashns/a1b40b04f5174a18bd05b17e3dffb0f0
- https://jvn.io/aakashns/fdaae0bf32cf4917a931ac415a5c31b0