Great news of the day (probably yesterday)! Google Bigquery Sandbox - comes for literally FREE - No Credit card required! From now, If you want to practice SQL, do it here!
Time to explore all nice public datasets there!
Announcement: https://lnkd.in/fk9rViV
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Time to explore all nice public datasets there!
Announcement: https://lnkd.in/fk9rViV
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
image_2019-02-09_11-45-26.png
5.6 MB
Here's a cheatsheet on Scikit-Learn (machine learning library that provides a range of supervised & unsupervised algorithms in #Python) and Caret package (used for solving any supervised machine learning problem in #R) we would like to share with you. #ScikitLearn #Caret https://lnkd.in/fgfR3FU
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Most of them use Python to solve data science problems. We may write code in Scripts or Notebook format.
People used to write in scripts. We have to run the entire code again and again which is a time taking process.
Now, everyone is using Jupyter notebooks. They are very useful and save time from executing the entire code. Instead, we can run individual chunks of code.
We need to be more productive in using this. If we don't know the shortcuts to use, we may waste a lot of time. So, it would be better if we know tips and shortcuts to use Jupyter notebook which makes us more productive at work.
Here is the resource to learn shortcuts.
28 Jupyter Notebook tips, tricks, and shortcuts: https://lnkd.in/f6VczRV
#datascience #python #datascience #machinelearning #artificialintelligence #data #deeplearning #jupyternotebook
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
People used to write in scripts. We have to run the entire code again and again which is a time taking process.
Now, everyone is using Jupyter notebooks. They are very useful and save time from executing the entire code. Instead, we can run individual chunks of code.
We need to be more productive in using this. If we don't know the shortcuts to use, we may waste a lot of time. So, it would be better if we know tips and shortcuts to use Jupyter notebook which makes us more productive at work.
Here is the resource to learn shortcuts.
28 Jupyter Notebook tips, tricks, and shortcuts: https://lnkd.in/f6VczRV
#datascience #python #datascience #machinelearning #artificialintelligence #data #deeplearning #jupyternotebook
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
“Still the seminal text on reinforcement learning - the increasingly important technique that underlies many of the most advanced AI systems today. Required reading for anyone seriously interested in the science of AI!”
―Demis Hassabis, Cofounder and CEO, DeepMind
“The second edition of Reinforcement Learning by Sutton and Barto comes at just the right time. The appetite for reinforcement learning among machine learning researchers has never been stronger, as the field has been moving tremendously in the last twenty years. If you want to fully understand the fundamentals of learning agents, this is the textbook to go to and get started with. It has been extended with modern developments in deep reinforcement learning while extending the scholarly history of the field to modern days. I will certainly recommend it to all my students and the many other graduate students and researchers who want to get the appropriate context behind the current excitement for RL.”
Yoshua Bengio, Professor of Computer Science and Operations Research, University of Montreal
#machinelearning #reinforcementlearning #artificialintelligence
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
―Demis Hassabis, Cofounder and CEO, DeepMind
“The second edition of Reinforcement Learning by Sutton and Barto comes at just the right time. The appetite for reinforcement learning among machine learning researchers has never been stronger, as the field has been moving tremendously in the last twenty years. If you want to fully understand the fundamentals of learning agents, this is the textbook to go to and get started with. It has been extended with modern developments in deep reinforcement learning while extending the scholarly history of the field to modern days. I will certainly recommend it to all my students and the many other graduate students and researchers who want to get the appropriate context behind the current excitement for RL.”
Yoshua Bengio, Professor of Computer Science and Operations Research, University of Montreal
#machinelearning #reinforcementlearning #artificialintelligence
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
MIT Deep Learning Basics: Introduction and Overview with TensorFlow
Blog by Lex Fridman: https://lnkd.in/e_5aVhD
#artificalintelligence #deeplearning #tensorflow
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Blog by Lex Fridman: https://lnkd.in/e_5aVhD
#artificalintelligence #deeplearning #tensorflow
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
When doing regression (or matching, or weighting, or whatever), don’t say “control for,” say “adjust for”
Blog post by Andrew Gelman, with a whole bunch of interesting comments to it
Link Review
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Blog post by Andrew Gelman, with a whole bunch of interesting comments to it
Link Review
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
On the "AI with AI" podcast, hosts Andy Ilachinski and David Broyles talk about my book.
Transcript: "One of the best self-contained texts that I've seen on machine learning. It's by Andriy Burkov, he's a PhD in AI and he's a senior data scientist and Machine Learning team leader at Gartner. He has written the hundred-page machine learning book (that's the title by the way) and it's a little bit over a hundred pages. If you go to its site, you can purchase a PDF directly for 20 dollars. You can either purchase a hard copy. Obviously, if you do purchase a hard copy you can send an email, according to the site, to the publisher and you will get a PDF for free. It is short, it's to the point, it has detail. If you are a seasoned practitioner this will bring you up to speed on related methods that you may immediately use. this.
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Transcript: "One of the best self-contained texts that I've seen on machine learning. It's by Andriy Burkov, he's a PhD in AI and he's a senior data scientist and Machine Learning team leader at Gartner. He has written the hundred-page machine learning book (that's the title by the way) and it's a little bit over a hundred pages. If you go to its site, you can purchase a PDF directly for 20 dollars. You can either purchase a hard copy. Obviously, if you do purchase a hard copy you can send an email, according to the site, to the publisher and you will get a PDF for free. It is short, it's to the point, it has detail. If you are a seasoned practitioner this will bring you up to speed on related methods that you may immediately use. this.
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
HOW TO LEARN PYTHON FOR DATA SCIENCE?
Someone ask me to update how to learn data science and please give R alternative as well, so I make it relevant to today standard
✅ Step 1
Building Learning Path
https://lnkd.in/fduvKgb
✅ Step 2
Download and Install Anaconda
https://lnkd.in/gWHY_ij
✅ Step 3
a. Learn the basics of Python (Lists, Tuples, Dictionaries, etc)
b. Understand the basics of data structures and algorithms
https://lnkd.in/gYKnJWN
✅ Step 4
Do more practice problems in Python
Codeacademy: https://lnkd.in/gGQ7cuv
✅ Step 5
Learn the scientific libraries (NumPy, SciPy, Pandas)
Pandas: https://lnkd.in/g4DFNpJ
✅ Step 6
Machine Learning with Scikit-Learn
Machine Learning in 20min: https://lnkd.in/g-Su_um
Scikit-Learn Tutorial: https://lnkd.in/gSThdRD
✅ Step 7:
Practice your machine learning skills
Kaggle Machine Learning Tutorial: https://lnkd.in/gT5nNwS
✅ Step 8:
Practice advanced library
a.PyTorch
https://lnkd.in/fzS52P9
b.TensorFlow
https://lnkd.in/fXKQkGy
c.Dlib
https://lnkd.in/fzPM2Gs
Kaggle Machine Learning Tutorial: https://lnkd.in/gT5nNwS
#machinelearning #datascience #python #scikitlearn #numpy #algorithms
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Someone ask me to update how to learn data science and please give R alternative as well, so I make it relevant to today standard
✅ Step 1
Building Learning Path
https://lnkd.in/fduvKgb
✅ Step 2
Download and Install Anaconda
https://lnkd.in/gWHY_ij
✅ Step 3
a. Learn the basics of Python (Lists, Tuples, Dictionaries, etc)
b. Understand the basics of data structures and algorithms
https://lnkd.in/gYKnJWN
✅ Step 4
Do more practice problems in Python
Codeacademy: https://lnkd.in/gGQ7cuv
✅ Step 5
Learn the scientific libraries (NumPy, SciPy, Pandas)
Pandas: https://lnkd.in/g4DFNpJ
✅ Step 6
Machine Learning with Scikit-Learn
Machine Learning in 20min: https://lnkd.in/g-Su_um
Scikit-Learn Tutorial: https://lnkd.in/gSThdRD
✅ Step 7:
Practice your machine learning skills
Kaggle Machine Learning Tutorial: https://lnkd.in/gT5nNwS
✅ Step 8:
Practice advanced library
a.PyTorch
https://lnkd.in/fzS52P9
b.TensorFlow
https://lnkd.in/fXKQkGy
c.Dlib
https://lnkd.in/fzPM2Gs
Kaggle Machine Learning Tutorial: https://lnkd.in/gT5nNwS
#machinelearning #datascience #python #scikitlearn #numpy #algorithms
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
New features from #DLI website we added a new menu page allow the user to easily find dataset and scientific paper from our website. First of all, read the scientific paper and find some match for our problem. After that find a good dataset and start to replicate the same model of the article. Once you did that, find the best implementation allow to fit with your specific problem. Enjoy Deep Learning!!! https://lnkd.in/dufCnMs
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
#AI approach outperformed human experts (AGAIN) in identifying #cervical precancer!
A research team led by investigators from the National Institutes of Health and Global Good has developed a #deeplearning #algorithm that can analyze digital images of a woman's cervix and accurately identify precancerous changes that require medical attention. This artificial intelligence (AI) approach, called automated visual evaluation, has the potential to revolutionize cervical cancer screening, particularly in low-resource settings.
To create the algorithm, the research team used more than 60,000 cervical images from an NCI archive of photos collected during a cervical cancer screening study that was carried out in Costa Rica in the 1990s.
Overall, the algorithm performed better than all standard screening tests at predicting all cases diagnosed during the Costa Rica study. Automated visual evaluation identified precancer with greater accuracy (AUC=0.91) than a human expert review (AUC=0.69) or conventional cytology (AUC=0.71).
Paper here: https://lnkd.in/dxETi8K
#algorithms #prediction #cancer #machinelearning #cnn #transferlearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
A research team led by investigators from the National Institutes of Health and Global Good has developed a #deeplearning #algorithm that can analyze digital images of a woman's cervix and accurately identify precancerous changes that require medical attention. This artificial intelligence (AI) approach, called automated visual evaluation, has the potential to revolutionize cervical cancer screening, particularly in low-resource settings.
To create the algorithm, the research team used more than 60,000 cervical images from an NCI archive of photos collected during a cervical cancer screening study that was carried out in Costa Rica in the 1990s.
Overall, the algorithm performed better than all standard screening tests at predicting all cases diagnosed during the Costa Rica study. Automated visual evaluation identified precancer with greater accuracy (AUC=0.91) than a human expert review (AUC=0.69) or conventional cytology (AUC=0.71).
Paper here: https://lnkd.in/dxETi8K
#algorithms #prediction #cancer #machinelearning #cnn #transferlearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Even a "simple" statistical procedure such as K-means isn't really that simple.
First, we need to clarify the objectives of the clustering and decide which of dozens of clustering methods to use. The K-means family is not always a good choice.
If we do decide to go with K-means, which type (e.g., K-means, K-medians)?
What are our candidate variables? Do they need to be re-coded or re-scaled? If so, how?
What range of cluster solutions to test?
What distance/similarity measures to use? There are dozens, it's not just Euclidean distance.
Initial seed selection - there are at least ten ways I know of.
The number of iterations and replications must also be decided.
Last but not least, interpreting the results and communicating our interpretations can make or break a cluster analysis.
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
First, we need to clarify the objectives of the clustering and decide which of dozens of clustering methods to use. The K-means family is not always a good choice.
If we do decide to go with K-means, which type (e.g., K-means, K-medians)?
What are our candidate variables? Do they need to be re-coded or re-scaled? If so, how?
What range of cluster solutions to test?
What distance/similarity measures to use? There are dozens, it's not just Euclidean distance.
Initial seed selection - there are at least ten ways I know of.
The number of iterations and replications must also be decided.
Last but not least, interpreting the results and communicating our interpretations can make or break a cluster analysis.
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Building your own PC for #AI #DeepLearning is 10x cheaper than renting out GPUs on cloud, so it seems.
We have been advising enterprises for quite a while about this "Build Your Own Deep Learning Monster" versus Buy dilemma. We've helped them save millions already with unique deployments already. (see full comparison here: https://lnkd.in/dn39Wr3)
Here are the options:
1. For instance, building your own cool deeplearning box at home costs merely $2900/- , just go to PCPartpicker and build your own configuration , here is an example: https://lnkd.in/dWxH2iJ
2. Building a monster at home can cost you a lot cheaper than the Nvidia DGX Super Station (Nvidia 64G GPU boxes sells from $50K to $70K
Do note that performance may vary if you build your own quad-GPU box at home.
#machinelearning #gpus #cloudml
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
We have been advising enterprises for quite a while about this "Build Your Own Deep Learning Monster" versus Buy dilemma. We've helped them save millions already with unique deployments already. (see full comparison here: https://lnkd.in/dn39Wr3)
Here are the options:
1. For instance, building your own cool deeplearning box at home costs merely $2900/- , just go to PCPartpicker and build your own configuration , here is an example: https://lnkd.in/dWxH2iJ
2. Building a monster at home can cost you a lot cheaper than the Nvidia DGX Super Station (Nvidia 64G GPU boxes sells from $50K to $70K
Do note that performance may vary if you build your own quad-GPU box at home.
#machinelearning #gpus #cloudml
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Solving an interesting probability problem using Python and tensorflow-probability, my new article in Towards Data Science (Online Publication)
https://lnkd.in/gH9pkUG
#probability #python #datascience #technology
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
https://lnkd.in/gH9pkUG
#probability #python #datascience #technology
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
The Best #FREE Books for Learning #DataScience
Link => bit.ly/AIFreeBooks
#ai #analytics #artificialinteligence #bi #bigdata #data #machinelearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Link => bit.ly/AIFreeBooks
#ai #analytics #artificialinteligence #bi #bigdata #data #machinelearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
image_2019-02-11_18-50-53.png
2.4 MB
Here's an infographic which displays most commonly used tools for data visualization by data scientists and data analysts for creating simple yet powerful visualizations! Download the infographic below. How many of them do you use? https://lnkd.in/fNVG4HW
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Here’s a list of 10 GREAT #SelfStarting #DataScience Projects to work on:
➖BEGINNER➖
⚠️ NOTE: The links provided will redirect you to a recommended Kaggle Kernel that I enjoyed. Use it as a reference before starting on your project :)
⚠️ IMPORTANT: Number 10 is a MUST DO!
1. Pokemon - Weedle's Cave 🐛
Python - https://lnkd.in/gcKWWQ2
2. Titanic ML 🚢
Python - https://lnkd.in/gafie9m
R - https://lnkd.in/gRRa7HV
3. Housing Prices Prediction 🏡
Python - https://lnkd.in/gX2FSDk
R - https://lnkd.in/ggFJSyd
➖INTERMEDIATE➖
4. Instacart Market Basket Analysis 🛒
Python - https://lnkd.in/gkNaXqH
R- https://lnkd.in/g2gthxu
5. Quora Question Pairs 👥
Project :https://lnkd.in/f3HQZsT
Tutorial (Python)- https://lnkd.in/fEzf-Xp
6. Human Resource Analytics 🕴🏻
Python - https://lnkd.in/gVUPfWm
R -https://lnkd.in/gHusQYX
➖ADVANCED➖
7. Analyzing Soccer Player Faces ⚽️
Python - https://lnkd.in/gUys_TS
8. Recruit Restaurant Visitor Forecasting 🍱
Python - https://lnkd.in/gjQvf74
9. TensorFlow Speech Recognition 🗣
Python - https://lnkd.in/g8SSPfW
➖MASTERY➖
10. Not Enough?
This is more complete guide from Analytics Vidhya
https://lnkd.in/g_QjzGe.
➖
Thanks!
#ml #tutorials #forecasting #analytics #guides
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
➖BEGINNER➖
⚠️ NOTE: The links provided will redirect you to a recommended Kaggle Kernel that I enjoyed. Use it as a reference before starting on your project :)
⚠️ IMPORTANT: Number 10 is a MUST DO!
1. Pokemon - Weedle's Cave 🐛
Python - https://lnkd.in/gcKWWQ2
2. Titanic ML 🚢
Python - https://lnkd.in/gafie9m
R - https://lnkd.in/gRRa7HV
3. Housing Prices Prediction 🏡
Python - https://lnkd.in/gX2FSDk
R - https://lnkd.in/ggFJSyd
➖INTERMEDIATE➖
4. Instacart Market Basket Analysis 🛒
Python - https://lnkd.in/gkNaXqH
R- https://lnkd.in/g2gthxu
5. Quora Question Pairs 👥
Project :https://lnkd.in/f3HQZsT
Tutorial (Python)- https://lnkd.in/fEzf-Xp
6. Human Resource Analytics 🕴🏻
Python - https://lnkd.in/gVUPfWm
R -https://lnkd.in/gHusQYX
➖ADVANCED➖
7. Analyzing Soccer Player Faces ⚽️
Python - https://lnkd.in/gUys_TS
8. Recruit Restaurant Visitor Forecasting 🍱
Python - https://lnkd.in/gjQvf74
9. TensorFlow Speech Recognition 🗣
Python - https://lnkd.in/g8SSPfW
➖MASTERY➖
10. Not Enough?
This is more complete guide from Analytics Vidhya
https://lnkd.in/g_QjzGe.
➖
Thanks!
#ml #tutorials #forecasting #analytics #guides
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
"Machine Learning from scratch!"
Implementation of some classic Machine Learning model from scratch and benchmarking against popular ML library, by Quan Tran: https://lnkd.in/er_ZNgY
#ArtificialIntelligence #DeepLearning #NeuralNetworks #MachineLearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Implementation of some classic Machine Learning model from scratch and benchmarking against popular ML library, by Quan Tran: https://lnkd.in/er_ZNgY
#ArtificialIntelligence #DeepLearning #NeuralNetworks #MachineLearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Deep Learning Drizzle
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
GitHub by Marimuthu K.: https://lnkd.in/eTUp4Hi
#artificialintelligence #deeplearning #machinelearning #reinforcementlearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Drench yourself in Deep Learning, Reinforcement Learning, Machine Learning, Computer Vision, and NLP by learning from these exciting lectures!!
GitHub by Marimuthu K.: https://lnkd.in/eTUp4Hi
#artificialintelligence #deeplearning #machinelearning #reinforcementlearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Can anyone recommend a good book, article, YouTube or other source that explains AI and machine learning in terms ordinary businessperson can understand?
There are many excellent resources for those with a good background in statistics, AI and machine learning , e.g., the classic Artificial Intelligence (Russell and Norvig), but they are too long or too technical for most folks.
At the other extreme, there are also many news articles, blogs, conference presentations and what I call airplane books that I find superficial or even misleading.
My reason for asking is that I am often asked this question myself but don't have a good answer. Thanks in advance for your thoughts.
Share With Me Please: @farzadHEYdaryy
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
There are many excellent resources for those with a good background in statistics, AI and machine learning , e.g., the classic Artificial Intelligence (Russell and Norvig), but they are too long or too technical for most folks.
At the other extreme, there are also many news articles, blogs, conference presentations and what I call airplane books that I find superficial or even misleading.
My reason for asking is that I am often asked this question myself but don't have a good answer. Thanks in advance for your thoughts.
Share With Me Please: @farzadHEYdaryy
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
Google's Open Images V4 is a publicly available dataset that contains 15.4M annotated bounding boxes for over 600 object categories. It has 1.9M images and is largest among all existing public image datasets with object location annotations.
We share a tutorial with a script for a fast downloader that allows you to filter and download images based on various classes and categories of your interest.
https://lnkd.in/gspXR6K
If you find this tool useful, please share.
#computervision #machinelearning #ai #training #objectdetection #deeplearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
We share a tutorial with a script for a fast downloader that allows you to filter and download images based on various classes and categories of your interest.
https://lnkd.in/gspXR6K
If you find this tool useful, please share.
#computervision #machinelearning #ai #training #objectdetection #deeplearning
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
A useful guide for all beginners in #machinelearning & #datascience - It lists down the most active data scientist on github, free books, ipython notebooks, tutorials on github. https://bit.ly/2I9xmvM
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv
✴️ @AI_Python_EN
❇️ @AI_Python
🗣 @AI_Python_arXiv