Streamlit dashboard to run SQL queries on BigQuery.
Blog post: https://imadelhanafi.com/posts/bigquery_dashboard/
Live version: https://bigquery.imadelhanafi.com
Github repo: https://github.com/imadelh/Bigquery-Streamlit
🔗 BigQuery dashboard with Streamlit :: Imad El Hanafi — Portfolio & Blog
Introduction Live version: https://bigquery.imadelhanafi.com Github repo: https://github.com/imadelh/Bigquery-Streamlit Storing and querying large datasets is an important step for data analysis and predictive modeling. BigQuery is a serverless data warehouse that allows storing data (up to Terabytes) and runs fast SQL queries without worrying about the computing power. In this post, we will discover how to interact with BigQuery and render results in an interactive dashboard built using Streamlit.
Blog post: https://imadelhanafi.com/posts/bigquery_dashboard/
Live version: https://bigquery.imadelhanafi.com
Github repo: https://github.com/imadelh/Bigquery-Streamlit
🔗 BigQuery dashboard with Streamlit :: Imad El Hanafi — Portfolio & Blog
Introduction Live version: https://bigquery.imadelhanafi.com Github repo: https://github.com/imadelh/Bigquery-Streamlit Storing and querying large datasets is an important step for data analysis and predictive modeling. BigQuery is a serverless data warehouse that allows storing data (up to Terabytes) and runs fast SQL queries without worrying about the computing power. In this post, we will discover how to interact with BigQuery and render results in an interactive dashboard built using Streamlit.
BigQuery dashboard with Streamlit
BigQuery dashboard with Streamlit :: Imad El Hanafi — Portfolio & Blog
Introduction Live version: https://bigquery.imadelhanafi.com
Github repo: https://github.com/imadelh/Bigquery-Streamlit
Storing and querying large datasets is an important step for data analysis and predictive modeling. BigQuery is a serverless data warehouse…
Github repo: https://github.com/imadelh/Bigquery-Streamlit
Storing and querying large datasets is an important step for data analysis and predictive modeling. BigQuery is a serverless data warehouse…
Analyzing and Improving the Image Quality of StyleGAN
https://github.com/NVlabs/stylegan2
Paper : https://arxiv.org/abs/1912.04958v1
https://paperswithcode.com/paper/analyzing-and-improving-the-image-quality-of
🔗 NVlabs/stylegan2
StyleGAN2 - Official TensorFlow Implementation. Contribute to NVlabs/stylegan2 development by creating an account on GitHub.
https://github.com/NVlabs/stylegan2
Paper : https://arxiv.org/abs/1912.04958v1
https://paperswithcode.com/paper/analyzing-and-improving-the-image-quality-of
🔗 NVlabs/stylegan2
StyleGAN2 - Official TensorFlow Implementation. Contribute to NVlabs/stylegan2 development by creating an account on GitHub.
GitHub
GitHub - NVlabs/stylegan2: StyleGAN2 - Official TensorFlow Implementation
StyleGAN2 - Official TensorFlow Implementation. Contribute to NVlabs/stylegan2 development by creating an account on GitHub.
Measuring Dataset Granularity.
http://arxiv.org/abs/1912.10154
🔗 Measuring Dataset Granularity
Despite the increasing visibility of fine-grained recognition in our field, "fine-grained'' has thus far lacked a precise definition. In this work, building upon clustering theory, we pursue a framework for measuring dataset granularity. We argue that dataset granularity should depend not only on the data samples and their labels, but also on the distance function we choose. We propose an axiomatic framework to capture desired properties for a dataset granularity measure and provide examples of measures that satisfy these properties. We assess each measure via experiments on datasets with hierarchical labels of varying granularity. When measuring granularity in commonly used datasets with our measure, we find that certain datasets that are widely considered fine-grained in fact contain subsets of considerable size that are substantially more coarse-grained than datasets generally regarded as coarse-grained. We also investigate the interplay between dataset granularity with a variety of factors an
http://arxiv.org/abs/1912.10154
🔗 Measuring Dataset Granularity
Despite the increasing visibility of fine-grained recognition in our field, "fine-grained'' has thus far lacked a precise definition. In this work, building upon clustering theory, we pursue a framework for measuring dataset granularity. We argue that dataset granularity should depend not only on the data samples and their labels, but also on the distance function we choose. We propose an axiomatic framework to capture desired properties for a dataset granularity measure and provide examples of measures that satisfy these properties. We assess each measure via experiments on datasets with hierarchical labels of varying granularity. When measuring granularity in commonly used datasets with our measure, we find that certain datasets that are widely considered fine-grained in fact contain subsets of considerable size that are substantially more coarse-grained than datasets generally regarded as coarse-grained. We also investigate the interplay between dataset granularity with a variety of factors an
Facebook has a neural network that can do advanced math
https://www.technologyreview.com/s/614929/facebook-has-a-neural-network-that-can-do-advanced-math/#
🔗 Facebook has a neural network that can do advanced math
Other neural nets haven’t progressed beyond simple addition and multiplication, but this one calculates integrals and solves differential equations.
https://www.technologyreview.com/s/614929/facebook-has-a-neural-network-that-can-do-advanced-math/#
🔗 Facebook has a neural network that can do advanced math
Other neural nets haven’t progressed beyond simple addition and multiplication, but this one calculates integrals and solves differential equations.
MIT Technology Review
Facebook has a neural network that can do advanced math
Here’s a challenge for the mathematically inclined among you. Solve the following differential equation for y: You have 30 seconds. Quick! No dallying. The answer, of course, is: If you were unable to find a solution, don’t feel too bad. This expression…
Visual Domain Adaptation Challenge
http://ai.bu.edu/visda-2019/?fbclid=IwAR1duIuADj053gRA5nPPG73K6wi1eh9DQfFUXSjVNzKeGNOleVpkPX6FywE
🔗 VisDA2019: Visual Domain Adaptation Challenge
We are pleased to announce the 2017 Visual Domain Adaptation (VisDA2017) Challenge! The VisDA challenge aims to test domain adaptation methods’ ability to transfer source knowledge and adapt it to novel target domains. The goal is to develop a method of unsupervised syntetic-to-real domain adaptation
http://ai.bu.edu/visda-2019/?fbclid=IwAR1duIuADj053gRA5nPPG73K6wi1eh9DQfFUXSjVNzKeGNOleVpkPX6FywE
🔗 VisDA2019: Visual Domain Adaptation Challenge
We are pleased to announce the 2017 Visual Domain Adaptation (VisDA2017) Challenge! The VisDA challenge aims to test domain adaptation methods’ ability to transfer source knowledge and adapt it to novel target domains. The goal is to develop a method of unsupervised syntetic-to-real domain adaptation
ai.bu.edu
VisDA2019: Visual Domain Adaptation Challenge
We are pleased to announce the 2017 Visual Domain Adaptation (VisDA2017) Challenge! The VisDA challenge aims to test domain adaptation methods’ ability to transfer source knowledge and adapt it to novel target domains. The goal is to develop a method of unsupervised…
Here's the original article if you want to know what it actually says. https://www.nature.com/articles/s41537-019-0077-9
🔗 A machine learning approach to predicting psychosis using semantic density and latent content analysis
A machine learning approach to predicting psychosis using semantic density and latent content analysis
🔗 A machine learning approach to predicting psychosis using semantic density and latent content analysis
A machine learning approach to predicting psychosis using semantic density and latent content analysis
Nature
A machine learning approach to predicting psychosis using semantic density and latent content analysis
Schizophrenia - A machine learning approach to predicting psychosis using semantic density and latent content analysis
“AI: Monte Carlo Tree Search (MCTS)”
https://rsci.app.link/LczXR6YnO2_p=c11731dc9a0660eee31c8de3e9b6b9
🔗 Medium – Get smarter about what matters to you.
Medium is not like any other platform on the internet. Our sole purpose is to help you find compelling ideas, knowledge, and perspectives. We don’t serve ads—we serve you, the curious reader who loves to learn new things. Medium is home to thousands of independent voices, and we combine humans and technology to find the best reading for you—and filter out the rest.
https://rsci.app.link/LczXR6YnO2_p=c11731dc9a0660eee31c8de3e9b6b9
🔗 Medium – Get smarter about what matters to you.
Medium is not like any other platform on the internet. Our sole purpose is to help you find compelling ideas, knowledge, and perspectives. We don’t serve ads—we serve you, the curious reader who loves to learn new things. Medium is home to thousands of independent voices, and we combine humans and technology to find the best reading for you—and filter out the rest.
Medium
Medium – Get smarter about what matters to you.
Medium is not like any other platform on the internet. Our sole purpose is to help you find compelling ideas, knowledge, and perspectives. We don’t serve ads—we serve you, the curious reader who loves to learn new things. Medium is home to thousands of independent…
CS 188 : Introduction to Artificial Intelligence
https://inst.eecs.berkeley.edu/~cs188/fa18/
🔗 CS 188: Introduction to Artificial Intelligence, Fall 2018
https://inst.eecs.berkeley.edu/~cs188/fa18/
🔗 CS 188: Introduction to Artificial Intelligence, Fall 2018
Long Short Term Memory and Gated Recurrent Unit’s Explained — ELI5 Way
🔗 Long Short Term Memory and Gated Recurrent Unit’s Explained — ELI5 Way
In this post, we will learn the intuition behind the working of LSTM and GRU.
🔗 Long Short Term Memory and Gated Recurrent Unit’s Explained — ELI5 Way
In this post, we will learn the intuition behind the working of LSTM and GRU.
Medium
Long Short Term Memory and Gated Recurrent Unit’s Explained — ELI5 Way
In this post, we will learn the intuition behind the working of LSTM and GRU.
Can You Become a Data Scientist Without a Quantitative Degree?
🔗 Can You Become a Data Scientist Without a Quantitative Degree?
A story and some insights
🔗 Can You Become a Data Scientist Without a Quantitative Degree?
A story and some insights
Medium
Can You Become a Data Scientist Without a Quantitative Degree?
A story and some insights
🎥 Data Science For Beginners with Python 6 - If Else and Looping Constructs in Pandas Part 1
👁 1 раз ⏳ 723 сек.
👁 1 раз ⏳ 723 сек.
Data Science For Beginners with Python 6 - Using If Else and Looping Constructs to modify the data in Pandas dataframe Part 1
Welcome to this course on Data Science For Beginners With Python. In video provides an Introduction to Data Science with Python- Copying, Selecting, Indexing data from pandas dataframes and different Attributes of Data in Pandas. What is Data Science?
Link to notebook and dataset: https://github.com/gshanbhag525/Programming-Knowledge-
Numpy tutorials: https://www.youtube.com/waVk
Data Science For Beginners with Python 6 - If Else and Looping Constructs in Pandas Part 1
Data Science For Beginners with Python 6 - Using If Else and Looping Constructs to modify the data in Pandas dataframe Part 1
Welcome to this course on Data Science For Beginners With Python. In video provides an Introduction to Data Science with Python…
Welcome to this course on Data Science For Beginners With Python. In video provides an Introduction to Data Science with Python…
🎥 Untitled
👁 4 раз ⏳ 2891 сек.
👁 4 раз ⏳ 2891 сек.
Vk
Машинное обучение, AI, нейронные сети, Big Data's Videos | VK
vk.com video
Standard Machine Learning Datasets for Imbalanced Classification
🔗 Standard Machine Learning Datasets for Imbalanced Classification
An imbalanced classification problem is a problem that involves predicting a class label where the distribution of class labels in the training dataset is skewed. Many real-world classification problems have an imbalanced class distribution, therefore it is important for machine learning practitioners to get familiar with working with these types of problems. In this tutorial, …
🔗 Standard Machine Learning Datasets for Imbalanced Classification
An imbalanced classification problem is a problem that involves predicting a class label where the distribution of class labels in the training dataset is skewed. Many real-world classification problems have an imbalanced class distribution, therefore it is important for machine learning practitioners to get familiar with working with these types of problems. In this tutorial, …
MachineLearningMastery.com
Standard Machine Learning Datasets for Imbalanced Classification - MachineLearningMastery.com
An imbalanced classification problem is a problem that involves predicting a class label where the distribution of class labels in the training dataset is skewed.
Many real-world classification problems have an imbalanced class distribution, therefore…
Many real-world classification problems have an imbalanced class distribution, therefore…
ИИ и будущее работы: перспективы занятости в ближайшем будущем
На конференции в MIT изучали компании, внедрившие дружественные к работникам ИИ
В начале декабря в MIT собирались эксперты, чтобы попытаться предсказать ту роль, которую искусственный интеллект (ИИ) будет играть в будущем рабочего процесса. Станет ли он врагом рабочего человека? Окажется ли спасителем? Или это просто будет очередная инновация, типа электричества или интернета?
Конференция под названием «Конгресс по ИИ и будущему работы», проходившая в аудитории Кресге в MIT, сделала довольно пессимистичные прогнозы по поводу пути развития ИИ, из-за которого он, судя по всему, будет уничтожать рабочие места и целые сектора индустрии. Робомобили оставит без работы дальнобойщиков; электронные клерки оставят без работы помощников юристов; роботы будут продолжать отнимать работу у рабочих на заводах и складах.
🔗 ИИ и будущее работы: перспективы занятости в ближайшем будущем
На конференции в MIT изучали компании, внедрившие дружественные к работникам ИИ В начале декабря в MIT собирались эксперты, чтобы попытаться предсказать ту рол...
На конференции в MIT изучали компании, внедрившие дружественные к работникам ИИ
В начале декабря в MIT собирались эксперты, чтобы попытаться предсказать ту роль, которую искусственный интеллект (ИИ) будет играть в будущем рабочего процесса. Станет ли он врагом рабочего человека? Окажется ли спасителем? Или это просто будет очередная инновация, типа электричества или интернета?
Конференция под названием «Конгресс по ИИ и будущему работы», проходившая в аудитории Кресге в MIT, сделала довольно пессимистичные прогнозы по поводу пути развития ИИ, из-за которого он, судя по всему, будет уничтожать рабочие места и целые сектора индустрии. Робомобили оставит без работы дальнобойщиков; электронные клерки оставят без работы помощников юристов; роботы будут продолжать отнимать работу у рабочих на заводах и складах.
🔗 ИИ и будущее работы: перспективы занятости в ближайшем будущем
На конференции в MIT изучали компании, внедрившие дружественные к работникам ИИ В начале декабря в MIT собирались эксперты, чтобы попытаться предсказать ту рол...
Хабр
ИИ и будущее работы: перспективы занятости в ближайшем будущем
На конференции в MIT изучали компании, внедрившие дружественные к работникам ИИ В начале декабря в MIT собирались эксперты, чтобы попытаться предсказать ту роль, которую искусственный интеллект...
Multi-Armed Bandits and Reinforcement Learning
A Gentle Introduction to the Classic Problem with Python Examples
Наш телеграм канал - tglink.me/ai_machinelearning_big_data
https://towardsdatascience.com/multi-armed-bandits-and-reinforcement-learning-dc9001dcb8da?source=collection_home---4------3-----------------------
🔗 Multi-Armed Bandits and Reinforcement Learning
A Gentle Introduction to the Classic Problem with Python Examples
A Gentle Introduction to the Classic Problem with Python Examples
Наш телеграм канал - tglink.me/ai_machinelearning_big_data
https://towardsdatascience.com/multi-armed-bandits-and-reinforcement-learning-dc9001dcb8da?source=collection_home---4------3-----------------------
🔗 Multi-Armed Bandits and Reinforcement Learning
A Gentle Introduction to the Classic Problem with Python Examples
9 способов дополнительного заработка для Data Scientist-а.
https://youtu.be/1FrY7ARSf10
🔗 9 Ways You Can Make Extra Income as a Data Scientist
In this video I talk about 9 ways I have used or seen others make extra income as a data scientist. These ways vary in difficulty, risk level, and the amount of money that you can make, but all of them have the potential to help you develop your skills and earn $$$. #DataScience #DataScienceJobs #DataScienceIncome 1) Write for medium or start your own blog. My Medium Articles: https://medium.com/@kenneth.b.jee 2) Complete in kaggle or topcoder competitions Kaggle: https://www.kaggle.com/competitions Top
https://youtu.be/1FrY7ARSf10
🔗 9 Ways You Can Make Extra Income as a Data Scientist
In this video I talk about 9 ways I have used or seen others make extra income as a data scientist. These ways vary in difficulty, risk level, and the amount of money that you can make, but all of them have the potential to help you develop your skills and earn $$$. #DataScience #DataScienceJobs #DataScienceIncome 1) Write for medium or start your own blog. My Medium Articles: https://medium.com/@kenneth.b.jee 2) Complete in kaggle or topcoder competitions Kaggle: https://www.kaggle.com/competitions Top
YouTube
9 Ways You Can Make Extra Income as a Data Scientist
In this video I talk about 9 ways I have used or seen others make extra income as a data scientist. These ways vary in difficulty, risk level, and the amount of money that you can make, but all of them have the potential to help you develop your skills and…
Как работают нейронные сети и почему они стали приносить большие деньги
Нейросети выросли от состояния академической диковинки до массивной индустрии
За последнее десятилетие компьютера заметно улучшили свои возможности в области понимания окружающего мира. ПО для фототехники автоматически распознаёт лица людей. Смартфоны преобразуют речь в текст. Робомобили распознают объекты на дороге и избегают столкновения с ними.
В основе всех этих прорывов лежит технология работы искусственного интеллекта (ИИ) под названием глубокое обучение (ГО). ГО основывается на нейросетях (НС), структурах данных, вдохновлённых сетями, составленными из биологических нейронов. НС организуются послойно, и входы одного слоя соединены с выходами соседнего.
Специалисты по информатике экспериментируют с НС с 1950-х годов. Однако основы сегодняшней обширной индустрии ГО заложили два крупных прорыва – один произошёл в 1986 году, второй – в 2012. Прорыв 2012 года – революция ГО – была связана с открытием того, что использование НС с большим количеством слоёв позволит нам значительно улучшить их эффективность. Открытию способствовали растущие объёмы как данных, так и вычислительных мощностей.
🔗 Как работают нейронные сети и почему они стали приносить большие деньги
Нейросети выросли от состояния академической диковинки до массивной индустрии За последнее десятилетие компьютера заметно улучшили свои возможности в области п...
Нейросети выросли от состояния академической диковинки до массивной индустрии
За последнее десятилетие компьютера заметно улучшили свои возможности в области понимания окружающего мира. ПО для фототехники автоматически распознаёт лица людей. Смартфоны преобразуют речь в текст. Робомобили распознают объекты на дороге и избегают столкновения с ними.
В основе всех этих прорывов лежит технология работы искусственного интеллекта (ИИ) под названием глубокое обучение (ГО). ГО основывается на нейросетях (НС), структурах данных, вдохновлённых сетями, составленными из биологических нейронов. НС организуются послойно, и входы одного слоя соединены с выходами соседнего.
Специалисты по информатике экспериментируют с НС с 1950-х годов. Однако основы сегодняшней обширной индустрии ГО заложили два крупных прорыва – один произошёл в 1986 году, второй – в 2012. Прорыв 2012 года – революция ГО – была связана с открытием того, что использование НС с большим количеством слоёв позволит нам значительно улучшить их эффективность. Открытию способствовали растущие объёмы как данных, так и вычислительных мощностей.
🔗 Как работают нейронные сети и почему они стали приносить большие деньги
Нейросети выросли от состояния академической диковинки до массивной индустрии За последнее десятилетие компьютера заметно улучшили свои возможности в области п...
Хабр
Как работают нейронные сети и почему они стали приносить большие деньги
Нейросети выросли от состояния академической диковинки до массивной индустрии За последнее десятилетие компьютеры заметно улучшили свои возможности в области п...
deeptraffic: DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
https://github.com/lexfridman/deeptraffic
🔗 lexfridman/deeptraffic
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series. - lexfridman/deeptraffic
https://github.com/lexfridman/deeptraffic
🔗 lexfridman/deeptraffic
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series. - lexfridman/deeptraffic
GitHub
GitHub - lexfridman/deeptraffic: DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series.
DeepTraffic is a deep reinforcement learning competition, part of the MIT Deep Learning series. - lexfridman/deeptraffic
"Differentiable Convex Optimization Layers"
CVXPY creates powerful new PyTorch and TensorFlow layers
https://locuslab.github.io/2019-10-28-cvxpylayers/
🔗 Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers
CVXPY creates powerful new PyTorch and TensorFlow layers
https://locuslab.github.io/2019-10-28-cvxpylayers/
🔗 Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers
locuslab.github.io
Differentiable Convex Optimization Layers
CVXPY creates powerful new PyTorch and TensorFlow layers
Neural-Symbolic Cognitive Reasoning
Authors: D'Avila Garcez, Artur S., Lamb, Luís C., Gabbay, Dov M -
https://www.springer.com/gp/book/9783540732457
🔗 Neural-Symbolic Cognitive Reasoning | Artur S. D'Avila Garcez | Springer
Humans are often extraordinary at performing practical reasoning. There are cases where the human computer, slow as it is, is faster than any artificial intelligence system. Are we faster because of the way we perceive knowledge as opposed to the way we represent it? The authors address this...
Authors: D'Avila Garcez, Artur S., Lamb, Luís C., Gabbay, Dov M -
https://www.springer.com/gp/book/9783540732457
🔗 Neural-Symbolic Cognitive Reasoning | Artur S. D'Avila Garcez | Springer
Humans are often extraordinary at performing practical reasoning. There are cases where the human computer, slow as it is, is faster than any artificial intelligence system. Are we faster because of the way we perceive knowledge as opposed to the way we represent it? The authors address this...
SpringerLink
Neural-Symbolic Cognitive Reasoning
Humans are often extraordinary at performing practical reasoning. There are cases where the human computer, slow as it is, is faster than any artificial intelligence system. Are we faster because of the way we perceive knowledge as opposed to the way we represent…