🎥 Unpacking Artificial Intelligence and Machine Learning
👁 1 раз ⏳ 3465 сек.
In this webinar, Dr Karsten Schulz, from the Digital Tech Institute, and Martin Richards, from the Digital Technologies Hub, unpack AI and Machine Learning. They clarify key terms and approaches, make connections with the Australian Curriculum and show ways how to implement AI in a classroom environment. They also talk about differences to ‘conventional’ coding and discuss what ‘typical’ application fields for AI have in common to help teachers decide if or when to use it. The webinar includes a small resou

​Disaster Watch: a crisis mapping platform to collect, evaluate, and publish disaster-related tweets

https://medium.com/tensorflow/disaster-watch-a-crisis-mapping-platform-to-collect-evaluate-and-publish-disaster-related-tweets-3f89e31e9180

🔗 Disaster Watch: a crisis mapping platform to collect, evaluate, and publish disaster-related tweets
A guest post by Abraham Poorazizi, Mahmood Khordoo, and Mahsa Amini

​Top 7 Machine Learning Methods that Every Data Scientist Must Know

🔗 Top 7 Machine Learning Methods that Every Data Scientist Must Know
In this digital era, now most of the manual tasks are being automated. Now, machine learning algorithms are helping computers perform…

🎥 Edward Grefenstette: Teaching Artificial Agents to Understand Language by Modelling Reward
👁 1 раз ⏳ 3123 сек.
Recent progress in Deep Reinforcement Learning has shown that agents can be taught complex behaviour and solve difficult tasks, such as playing video games from pixel observations, or mastering the game of Go without observing human games, with relatively little prior information. Building on these successes, researchers such as Hermann and colleagues have sought to apply these methods to teach–in simulation–agents to complete a variety of tasks specified by combinatorially rich instruction languages. In th

🎥 [DeepBayes2019]: Day 1, Practical session 2. Bayesian reasoning
👁 1 раз ⏳ 1277 сек.
Speaker: Ekaterina Lobacheva

​Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification

https://arxiv.org/abs/1908.11860

🔗 Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target
Aspect-Target Sentiment Classification (ATSC) is a subtask of Aspect-Based Sentiment Analysis (ABSA), which has many applications e.g. in e-commerce, where data and insights from reviews can be leveraged to create value for businesses and customers. Recently, deep transfer-learning methods have been applied successfully to a myriad of Natural Language Processing (NLP) tasks, including ATSC. Building on top of the prominent the BERT language model, we approach ATSC by using a two-step procedure: Self-supervised domain-specific BERT language model finetuning, followed by supervised task-specific finetuning. Our findings on how to best exploit domain-specific language model finetuning enables us to produce new state-of-the-art performance on the SemEval 2014 Task 4 restaurants dataset. In addition, to explore the real-world robustness of our models, we perform cross-domain evaluation. We show that a cross-domain adapted BERT language model performs significantly better compared to strong baseline models like van

​Финал соревнования по машинному обучению от Яндекс Контест — Кирилл Бродт

🔗 Финал соревнования по машинному обучению от Яндекс Контест — Кирилл Бродт
Кирилл Бродт рассказывает про участие в финале ежегодного соревнования по машинному обучению от Яндекс Контест. Из этого видео вы узнаете, как подкрутить бейзлайн в рекомендательных системах и занять победное первое место. Узнать о текущих соревнованиях можно на сайте http://mltrainings.ru/ Узнать о новых тренировках и видео можно из групп: ВКонтакте https://vk.com/mltrainings Facebook https://www.facebook.com/groups/1413405125598651/ Telegram https://xn--r1a.website/mltrainings

​This Controllable AI Synthesizes Images For You

🔗 This Controllable AI Synthesizes Images For You
📷 We are now available on Instagram: https://www.instagram.com/twominutepapers/ 📝 The paper "On the steerability of generative adversarial networks" is available here: https://ali-design.github.io/gan_steerability/ ❤️ Pick up cool perks on our Patreon page: https://www.patreon.com/TwoMinutePapers 🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible: Alex Haro, Andrew Melnychuk, Angelos Evripiotis, Anthony Vdovitchenko, Brian Gilman, Bruno Brito, Bryan Learn, Christ

​Yann LeCun: Sophia and Does AI Need a Body? | AI Podcast Clips

🔗 Yann LeCun: Sophia and Does AI Need a Body? | AI Podcast Clips
This is a clip from a conversation with Yann LeCun on the Artificial Intelligence podcast. You can watch the full conversation here: http://bit.ly/2NJiCov If you enjoy these, consider subscribing, sharing, and commenting below. Full episode: http://bit.ly/2NJiCov Full episodes playlist: http://bit.ly/2EcbaKf Clips playlist: http://bit.ly/2JYkbfZ Podcast website: https://lexfridman.com/ai Yann LeCun is one of the fathers of deep learning, the recent revolution in AI that has captivated the world with the p

​Evading Machine Learning Malware Classifiers

🔗 Evading Machine Learning Malware Classifiers
for fun and profit!

​Single UserID Matching for Anonymous Users Across Devices with GraphX

🔗 Single UserID Matching for Anonymous Users Across Devices with GraphX
How to implement a probabilistic session similarity to create a single user ID for cross-device and anonymous user identification

🎥 Martin Christen - Geospatial Analysis using Python and JupyterHub
👁 1 раз ⏳ 1806 сек.
"Geospatial Analysis using Python and JupyterHub
[EuroPython 2019 - Talk - 2019-07-10 - Singapore [PyData track]
[Basel, CH]

By Martin Christen

Geospatial data is data containing a spatial component – describing objects with a reference to the planet's surface. This data usually consists of a spatial component, of various attributes, and sometimes of a time reference (where, what, and when). Efficient processing and visualization of small to large-scale spatial data is a challenging task.

This talk desc

🎥 Franziska Oschmann - Boosting research with machine learning.
👁 1 раз ⏳ 1802 сек.
"Boosting research with machine learning.
[EuroPython 2019 - Talk - 2019-07-10 - Osaka / Samarkand [PyData track]
[Basel, CH]

By Franziska Oschmann

Within the last 20 years machine learning (ML) experienced a boost in its impact on our daily lives. With the help of supervised and unsupervised methods tasks like computer vision, recognition of speech or text have been revolutionized. Due to this high impact of ML ongoing research focuses on the constant improvement of these methods.
However, ML is not exc

🎥 TensorFlow 2.0 Tutorial for Beginners 10 - Breast Cancer Detection Using CNN in Python
👁 1 раз ⏳ 1273 сек.
# Breast-Cancer-Detection-Using-CNN-in-Python
Breast Cancer Detection Using CNN in Python

Download Working File: https://github.com/laxmimerit/Breast-Cancer-Detection-Using-CNN-in-Python

natural image classification techniques and Artificial Intelligence methods has largely been used for the breast cancer classification task. The involvement CNN classification allows the doctor and the physicians a second opinion, and it saves the doctors' and physicians' time.

In this lesson, I have taught you how you c

​CS224N: Natural Language Processing with Deep Learning

https://onlinehub.stanford.edu/

🔗 Stanford Articitial Intelligence Online
Welcome to the Stanford AI Content Hub!

​Феерический screensaver для Kodi

Назначение хранителя экрана для «Kodi»

Проект предназначен для создания «Феерического» хранителя экрана с минимальным количеством исходного кода на языке Python. Проект является простейшим плагином для мультимедиа центра Kodi.

Проект показывает как можно создать очень красивый хранитель экрана целиком опираясь на работу «OpenSource» сообщества. Проект интеграционный, это пример написания двух независимых компонентов, каждый из которых занимает порядка 80 строчек кода. Первый компонент — генератор контента, shell скрипт, второй компонент — плагин для мультимедиа центра Kodi, отвечает за отображение контента.

Ну и напоследок если вы программист и используете систему контроля версий Git, то вы можете визуализировать вашу работу, записать ее в видео файл и наслаждаться полученным результатом на экране телевизора или компьютера, откинувшись на спинку кресла с чашечкой кофе. А прохладными осенними вечерами вы можете убаюкивающе засыпать под ваш screensaver, не забыв при этом поставить таймер выключения устройства в Kodi.
https://habr.com/ru/post/466067/

🔗 Феерический screensaver для Kodi
Назначение хранителя экрана для «Kodi» Проект предназначен для создания «Феерического» хранителя экрана с минимальным количеством исходного кода на языке Python...

😃 😃 @ 😃 😃 @ 😃 😃

​Открылся набор в Академию больших данных MADE от Mailru Group. Академия создана экспертами из индустрии и научного мира специально для тех, у кого уже есть опыт работы в IT. Для тех, кто поступит, обучение будет полностью бесплатным.

Можно выбрать очную или дистанционную форму обучения, а также одну из трех специальностей: Data Scientist, Machine Learning Engineer и Data Engineer. Обучение займет полтора года, с октября 2019 по январь 2021 года.

Учащихся ждет продвинутый курс, включающий в себя занятия по прикладному анализу данных, разработке моделей машинного обучения для высоконагруженных сервисов, обработке больших данных, компьютерному зрению, обработке естественного языка, распознаванию речи и пр.

Условия поступления и подробности об Академии https://vk.cc/9G5rCN

🔗 Академия больших данных MADE
Академия больших данных MADE — бесплатный образовательный проект от Mail.ru Group в области Data Science и Big Data. Он разработан экспертами из индустрии и научного мира специально для специалистов с опытом работы в IT.

​Characterizing Bias in Classifiers using Generative Models
Models that are learned from real-world data are often biased because the
data used to train them is biased. This can propagate systemic human biases
https://arxiv.org/abs/1906.11891

🔗 Characterizing Bias in Classifiers using Generative Models
Models that are learned from real-world data are often biased because the data used to train them is biased. This can propagate systemic human biases that exist and ultimately lead to inequitable treatment of people, especially minorities. To characterize bias in learned classifiers, existing approaches rely on human oracles labeling real-world examples to identify the "blind spots" of the classifiers; these are ultimately limited due to the human labor required and the finite nature of existing image examples. We propose a simulation-based approach for interrogating classifiers using generative adversarial models in a systematic manner. We incorporate a progressive conditional generative model for synthesizing photo-realistic facial images and Bayesian Optimization for an efficient interrogation of independent facial image classification systems. We show how this approach can be used to efficiently characterize racial and gender biases in commercial systems.