Bringing data to life — let them tell their story with data visualisation
🔗 Bringing data to life — let them tell their story with data visualisation
Data visualisation requires technical skills, knowledge of some advanced chart types and the ability to tell stories with data.
🔗 Bringing data to life — let them tell their story with data visualisation
Data visualisation requires technical skills, knowledge of some advanced chart types and the ability to tell stories with data.
Medium
Bringing data to life — let them tell their story with data visualisation
Data visualisation requires technical skills, knowledge of some advanced chart types and the ability to tell stories with data.
Beginner’s Guide to Machine Learning with Python
🔗 Beginner’s Guide to Machine Learning with Python
Machine Learning, a prominent topic in Artificial Intelligence domain, has been in the spotlight for quite some time now. This area may…
🔗 Beginner’s Guide to Machine Learning with Python
Machine Learning, a prominent topic in Artificial Intelligence domain, has been in the spotlight for quite some time now. This area may…
Towards Data Science
Beginner’s Guide to Machine Learning with Python
Machine Learning, a prominent topic in Artificial Intelligence domain, has been in the spotlight for quite some time now. This area may…
🎥 Launching a Data Science Project: Cleaning is Half the Battle by Kevin Feasel
👁 1 раз ⏳ 4748 сек.
👁 1 раз ⏳ 4748 сек.
Please note that this a recorded webinar. It was recorded during live presentation.
There’s an old adage in software development: Garbage In, Garbage Out. This adage certainly applies to data science projects: if you simply throw raw data at models, you will end up with garbage results. In this session, we will build an understanding of just what it takes to implement a data science project whose results are not garbage. We will the Microsoft Team Data Science Process as our model for project implementatioVk
Launching a Data Science Project: Cleaning is Half the Battle by Kevin Feasel
Please note that this a recorded webinar. It was recorded during live presentation.
There’s an old adage in software development: Garbage In, Garbage Out. This adage certainly applies to data science projects: if you simply throw raw data at models, you…
There’s an old adage in software development: Garbage In, Garbage Out. This adage certainly applies to data science projects: if you simply throw raw data at models, you…
https://www.youtube.com/watch?v=-RtcM0oz1lQ\
🎥 NSDI '19 - Tiresias: A GPU Cluster Manager for Distributed Deep Learning
👁 1 раз ⏳ 1449 сек.
🎥 NSDI '19 - Tiresias: A GPU Cluster Manager for Distributed Deep Learning
👁 1 раз ⏳ 1449 сек.
Juncheng Gu, Mosharaf Chowdhury, and Kang G. Shin, University of Michigan, Ann Arbor; Yibo Zhu, Microsoft and Bytedance; Myeongjae Jeon, Microsoft and UNIST; Junjie Qian, Microsoft; Hongqiang Liu, Alibaba; Chuanxiong Guo, Bytedance
Deep learning (DL) training jobs bring some unique challenges to existing cluster managers, such as unpredictable training times, an all-or-nothing execution model, and inflexibility in GPU sharing. Our analysis of a large GPU cluster in production shows that existing big data sYouTube
NSDI '19 - Tiresias: A GPU Cluster Manager for Distributed Deep Learning
Juncheng Gu, Mosharaf Chowdhury, and Kang G. Shin, University of Michigan, Ann Arbor; Yibo Zhu, Microsoft and Bytedance; Myeongjae Jeon, Microsoft and UNIST;...
🎥 NSDI '19 - JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative
👁 1 раз ⏳ 1561 сек.
👁 1 раз ⏳ 1561 сек.
Eunji Jeong, Sungwoo Cho, Gyeong-In Yu, Joo Seong Jeong, Dong-Jin Shin, and Byung-Gon Chun, Seoul National University
The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the requirement of quickly executing large computations, but also to support straightforward programming models for quickly implementing and experimenting with complex network structures. However, existing frameworks fail to excel in both departments simultaneously, leading to divergedVk
NSDI '19 - JANUS: Fast and Flexible Deep Learning via Symbolic Graph Execution of Imperative
Eunji Jeong, Sungwoo Cho, Gyeong-In Yu, Joo Seong Jeong, Dong-Jin Shin, and Byung-Gon Chun, Seoul National University
The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the requirement of quickly executing…
The rapid evolution of deep neural networks is demanding deep learning (DL) frameworks not only to satisfy the requirement of quickly executing…
🎥 Deep Learning and Blockchain w/ Insight AI Fellows, Michelle Bonat 20190325
👁 1 раз ⏳ 5012 сек.
👁 1 раз ⏳ 5012 сек.
Michelle Bonat, CEO & Co-Founder, Data Simply, Inc.
Josh Deetz, Physical Data Scientist, Carbon
Khyati Ganatra, Data Scientist at Cequence Security
Deep learning can seem like a dark art. The reality is that it is very achievable to get a model working and predicting well. But deep learning also has some myths and pitfalls of which you should be aware. Michelle Bonat will walk through a project she did to predict cryptocurrency flows using deep learning and blockchain data. This includes code snippets andVk
Deep Learning and Blockchain w/ Insight AI Fellows, Michelle Bonat 20190325
Michelle Bonat, CEO & Co-Founder, Data Simply, Inc.
Josh Deetz, Physical Data Scientist, Carbon
Khyati Ganatra, Data Scientist at Cequence Security
Deep learning can seem like a dark art. The reality is that it is very achievable to get a model working and…
Josh Deetz, Physical Data Scientist, Carbon
Khyati Ganatra, Data Scientist at Cequence Security
Deep learning can seem like a dark art. The reality is that it is very achievable to get a model working and…
🎥 L19/2 Recurrent Neural Networks in Python
👁 2 раз ⏳ 2273 сек.
👁 2 раз ⏳ 2273 сек.
Dive into Deep Learning
UC Berkeley, STAT 157
Slides are at
http://courses.d2l.ai
The book is at
http://www.d2l.ai
RNN in PythonVk
L19/2 Recurrent Neural Networks in Python
Dive into Deep Learning
UC Berkeley, STAT 157
Slides are at
http://courses.d2l.ai
The book is at
http://www.d2l.ai
RNN in Python
UC Berkeley, STAT 157
Slides are at
http://courses.d2l.ai
The book is at
http://www.d2l.ai
RNN in Python
🎥 Positive-Unlabeled Learning
👁 23 раз ⏳ 3104 сек.
👁 23 раз ⏳ 3104 сек.
Мы поговорим о проблеме машинного обучения известной как Positive-Unlabeled learning. Сперва обсудим, что проблема из себя представляет и где может встречаться. Затем, я представлю разработанный мной метод для решения этой проблемы. Для понимания потребуются базовые знания о теории вероятности и классификации.
Ссылка на препринт: https://arxiv.org/pdf/1902.06965.pdf
Докладчик: Дмитрий Иванов.
Ссылка на слайды: https://research.jetbrains.org/files/material/5cac988ca384a.pdfVk
Positive-Unlabeled Learning
Мы поговорим о проблеме машинного обучения известной как Positive-Unlabeled learning. Сперва обсудим, что проблема из себя представляет и где может встречаться. Затем, я представлю разработанный мной метод для решения этой проблемы. Для понимания потребуются…
Building Your First Neural Network Using Keras
🔗 Building Your First Neural Network Using Keras
Removing the mysticism behind Neural Networks. Follow along and build your first Neural Net using Python & Keras.
🔗 Building Your First Neural Network Using Keras
Removing the mysticism behind Neural Networks. Follow along and build your first Neural Net using Python & Keras.
Towards Data Science
Building Your First Neural Network Using Keras
Removing the mysticism behind Neural Networks. Follow along and build your first Neural Net using Python & Keras.
🎥 Deep Learning на пальцах 8 - Metric Learning, Autoencoders, GANs
👁 24 раз ⏳ 5622 сек.
👁 24 раз ⏳ 5622 сек.
Курс: http://dlcourse.ai
Слайды: https://www.dropbox.com/s/n25eai8ivlq60bh/Lecture%208%20-%20Metric%20and%20Unsupervised.pdf?dl=0Vk
Deep Learning на пальцах 8 - Metric Learning, Autoencoders, GANs
Курс: http://dlcourse.ai
Слайды: https://www.dropbox.com/s/n25eai8ivlq60bh/Lecture%208%20-%20Metric%20and%20Unsupervised.pdf?dl=0
Слайды: https://www.dropbox.com/s/n25eai8ivlq60bh/Lecture%208%20-%20Metric%20and%20Unsupervised.pdf?dl=0
Time Series Feature Extraction for industrial big data (IIoT) applications
🔗 Time Series Feature Extraction for industrial big data (IIoT) applications
Feature Extraction by Distributed and Parallel means for industrial big data applications
🔗 Time Series Feature Extraction for industrial big data (IIoT) applications
Feature Extraction by Distributed and Parallel means for industrial big data applications
Towards Data Science
Time Series Feature Extraction for industrial big data (IIoT) applications
Feature Extraction by Distributed and Parallel means for industrial big data applications
🎥 What's New in TensorFlow, and How GCP Developers Benefit (Cloud Next '19)
👁 1 раз ⏳ 2368 сек.
👁 1 раз ⏳ 2368 сек.
TensorFlow 2.0 has landed!
During this session, you will learn all about TensorFlow 2.0's new features, usability enhancements, and performance increases - many of which are specifically optimized for cloud platforms.
We will use the TF2.0 migration tool to transition a model from TensorFlow 1.x to 2.0, and deploy an end-to-end machine learning model to Google Cloud Platform.
If you're interested in using TensorFlow for your deep learning experiments on GCP, you won't want to miss this talk!
Big Data AnVk
What's New in TensorFlow, and How GCP Developers Benefit (Cloud Next '19)
TensorFlow 2.0 has landed!
During this session, you will learn all about TensorFlow 2.0's new features, usability enhancements, and performance increases - many of which are specifically optimized for cloud platforms.
We will use the TF2.0 migration tool…
During this session, you will learn all about TensorFlow 2.0's new features, usability enhancements, and performance increases - many of which are specifically optimized for cloud platforms.
We will use the TF2.0 migration tool…
Multi-Class Text Classification with LSTM
🔗 Multi-Class Text Classification with LSTM
How to develop LSTM recurrent neural network models for text classification problems in Python using Keras deep learning library
🔗 Multi-Class Text Classification with LSTM
How to develop LSTM recurrent neural network models for text classification problems in Python using Keras deep learning library
Towards Data Science
Multi-Class Text Classification with LSTM
How to develop LSTM recurrent neural network models for text classification problems in Python using Keras deep learning library
🎥 GOTO 2018 • Augmented Reality and Machine Learning Cooperation on Mobile • Mourad Sidky
👁 1 раз ⏳ 2087 сек.
👁 1 раз ⏳ 2087 сек.
This presentation was recorded at GOTO Copenhagen 2018. #gotocon #gotocph
http://gotocph.com
Mourad Sidky - iOS Tech Lead at Groupon
ABSTRACT
Mobile devices are getting more and more powerful, with not-only advanced hardware, but also intelligent operating systems and high-performance compatible set of native frameworks. Mobile devices are capable of doing expensive on-device processing to achieve augmented reality and machine learning, without the need to communicate to any other external services.
AppleVk
GOTO 2018 • Augmented Reality and Machine Learning Cooperation on Mobile • Mourad Sidky
This presentation was recorded at GOTO Copenhagen 2018. #gotocon #gotocph
http://gotocph.com
Mourad Sidky - iOS Tech Lead at Groupon
ABSTRACT
Mobile devices are getting more and more powerful, with not-only advanced hardware, but also intelligent operating…
http://gotocph.com
Mourad Sidky - iOS Tech Lead at Groupon
ABSTRACT
Mobile devices are getting more and more powerful, with not-only advanced hardware, but also intelligent operating…
🎥 Deep Dive into Machine Learning in ArcGIS Platform
👁 1 раз ⏳ 15932 сек.
👁 1 раз ⏳ 15932 сек.
In this hands-on workshop, you will be exposed to machine learning in the ArcGIS Platform (Pro and Online), in addition to Python integration to leverage powerful machine learning and deep learning libraries. You will learn advanced use patterns and best practices for machine learning tools in ArcGIS Pro, in addition to best practices for integrating external machine learning libraries. After this workshop you will be equipped with:
- Workflows for setting up a machine learning environment in your computerVk
Deep Dive into Machine Learning in ArcGIS Platform
In this hands-on workshop, you will be exposed to machine learning in the ArcGIS Platform (Pro and Online), in addition to Python integration to leverage powerful machine learning and deep learning libraries. You will learn advanced use patterns and best…
The Power of A/B Testing
🔗 The Power of A/B Testing
A visual summary of how sample size, effect size and significance level affect the power of A/B testing
🔗 The Power of A/B Testing
A visual summary of how sample size, effect size and significance level affect the power of A/B testing
Towards Data Science
The Power of A/B Testing
A visual summary of how sample size, effect size and significance level affect the power of A/B testing
Generalizable Deep Reinforcement Learning
🔗 Generalizable Deep Reinforcement Learning
What Google AI’s PlaNet AI means for reinforcement learning research and how transfer learning plays a key role
🔗 Generalizable Deep Reinforcement Learning
What Google AI’s PlaNet AI means for reinforcement learning research and how transfer learning plays a key role
Towards Data Science
Everything you need to know about Google’s new PlaNet reinforcement learning network
What Google AI’s PlaNet AI means for reinforcement learning research and how transfer learning plays a key role
Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов
🔗 Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов
В ноябре я публиковал статью «Яндекс.Метеум – технология без технологии. Маркетинг с точностью до района», где соотносил качество прогнозов Яндекса с другими сер...
🔗 Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов
В ноябре я публиковал статью «Яндекс.Метеум – технология без технологии. Маркетинг с точностью до района», где соотносил качество прогнозов Яндекса с другими сер...
Хабр
Насколько точно Яндекс прогнозирует осадки зимой? Анализируем точность прогностических сервисов
В ноябре я публиковал статью «Яндекс.Метеум – технология без технологии. Маркетинг с точностью до района» , где соотносил качество прогнозов Яндекса с другими сервиса. Акцент делался на температуре,...
Step Change Improvement in Molecular Property Prediction with PotentialNet
🔗 Step Change Improvement in Molecular Property Prediction with PotentialNet
TL;DR: Pande Lab in collaboration with Merck shows marked increase in ADMET Prediction accuracy with PotentialNet
🔗 Step Change Improvement in Molecular Property Prediction with PotentialNet
TL;DR: Pande Lab in collaboration with Merck shows marked increase in ADMET Prediction accuracy with PotentialNet
Medium
Step Change Improvement in Molecular Property Prediction with PotentialNet
TL;DR: Pande Lab in collaboration with Merck shows marked increase in ADMET Prediction accuracy with PotentialNet
🎥 TensorFlow 2.0 - Introductory Tutorial
👁 3 раз ⏳ 588 сек.
👁 3 раз ⏳ 588 сек.
TensorFlow 2.0 is here! Let's take a look at a simple tutorial on the basics of TensorFlow.
The code is available at the GitHub repository for the series:
If you do have any questions with what we covered in this video then feel free to ask in the comment section below & I'll do my best to answer those.
If you enjoy these tutorials & would like to support them then the easiest way is to simply like the video & give it a thumbs up & also it's a huge help to share these videos with anyone who you think wouVk
TensorFlow 2.0 - Introductory Tutorial
TensorFlow 2.0 is here! Let's take a look at a simple tutorial on the basics of TensorFlow.
The code is available at the GitHub repository for the series:
If you do have any questions with what we covered in this video then feel free to ask in the comment…
The code is available at the GitHub repository for the series:
If you do have any questions with what we covered in this video then feel free to ask in the comment…