Forwarded from Cool GitHub repositories
labmlai/annotated_deep_learning_paper_implementatios
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations
Creator: labml.ai
Stars ⭐️: 7.8k
Forked By: 703
GithubRepo: https://github.com/labmlai/annotated_deep_learning_paper_implementations
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @github_repositories_bds for more cool repositories.
*This channel belongs to @bigdataspecialist group
This is a collection of simple PyTorch implementations of neural networks and related algorithms. These implementations are documented with explanations
Creator: labml.ai
Stars ⭐️: 7.8k
Forked By: 703
GithubRepo: https://github.com/labmlai/annotated_deep_learning_paper_implementations
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @github_repositories_bds for more cool repositories.
*This channel belongs to @bigdataspecialist group
GitHub
GitHub - labmlai/annotated_deep_learning_paper_implementations: 🧑🏫 60+ Implementations/tutorials of deep learning papers with…
🧑🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), ga...
A LITTLE GUIDE TO HANDLING MISSING DATA
Having any Feature missing more than 5-10% of its values? you should consider it to be missing data or feature with high absence rate👀
How can you handle these missing values, ensuring you dont loose important part of your data🤷♀️
Not a problem😌. Here are important facts you must know😉
✍️Instances with missing values for all features should be eliminated
✍️Features with high absence rate should either be eliminated or filled with values
✍️Missing values can be replaced using Mean Imputation or Regression Imputation
✍️ Be careful with mean imputation for it may introduce bias as it evens out all instances
✍️Regression Imputation might overfit your model
✍️Mean and Regression Imputation can't be applied to Text features with missing values
✍️Text Features with missing values can be eliminated if not needed in data
✍️Important Text Features with Missing values can be replaced with a new class or category labelled as uncategorized
Having any Feature missing more than 5-10% of its values? you should consider it to be missing data or feature with high absence rate👀
How can you handle these missing values, ensuring you dont loose important part of your data🤷♀️
Not a problem😌. Here are important facts you must know😉
✍️Instances with missing values for all features should be eliminated
✍️Features with high absence rate should either be eliminated or filled with values
✍️Missing values can be replaced using Mean Imputation or Regression Imputation
✍️ Be careful with mean imputation for it may introduce bias as it evens out all instances
✍️Regression Imputation might overfit your model
✍️Mean and Regression Imputation can't be applied to Text features with missing values
✍️Text Features with missing values can be eliminated if not needed in data
✍️Important Text Features with Missing values can be replaced with a new class or category labelled as uncategorized
Forwarded from Free programming books
Please open Telegram to view this post
VIEW IN TELEGRAM
UDEMY FREE DEEP LEARNING COURSE
Python for Deep Learning: Build Neural Networks in Python
Rating ⭐️: 4.2 out of 5
Students 👨🏫: 44,894
Created by: Meta Brains
🔗 Course link
Note: Free coupon is inserted in URL. Courses are FREE FOR FIRST 1000 enrollments
#python #datanalysis #datascience #deeplearing
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group
Python for Deep Learning: Build Neural Networks in Python
Rating ⭐️: 4.2 out of 5
Students 👨🏫: 44,894
Created by: Meta Brains
🔗 Course link
Note: Free coupon is inserted in URL. Courses are FREE FOR FIRST 1000 enrollments
#python #datanalysis #datascience #deeplearing
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group
Artificial Neural Networks (ANN) with Keras in Python and R
Rating ⭐️: 4.7 out of 5
Duration ⏰: 11 hours on-demand video
Students 👨🏫: 143,495
Created by: Start-Tech Academy
🔗 Course link
Note: Free coupon is inserted in URL. Courses are FREE FOR FIRST 1000 enrollments
#ai #ml #neural_networks #machine_learning #data_science #deep_learning
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group
Rating ⭐️: 4.7 out of 5
Duration ⏰: 11 hours on-demand video
Students 👨🏫: 143,495
Created by: Start-Tech Academy
🔗 Course link
Note: Free coupon is inserted in URL. Courses are FREE FOR FIRST 1000 enrollments
#ai #ml #neural_networks #machine_learning #data_science #deep_learning
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group
microsoft/Data-Science-For-Beginners
Azure Cloud Advocates at Microsoft are pleased to offer a 10-week, 20-lesson curriculum all about Data Science. Each lesson includes pre-lesson and post-lesson quizzes, written instructions to complete the lesson, a solution, and an assignment. Our project-based pedagogy allows you to learn while building, a proven way for new skills to 'stick'.
Creator: Microsoft
Stars ⭐️: 11.1k
Forked By: 1.9k
GithubRepo: https://github.com/microsoft/Data-Science-For-Beginners
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @github_repositories_bds for more cool repositories.
*This channel belongs to @bigdataspecialist group
Azure Cloud Advocates at Microsoft are pleased to offer a 10-week, 20-lesson curriculum all about Data Science. Each lesson includes pre-lesson and post-lesson quizzes, written instructions to complete the lesson, a solution, and an assignment. Our project-based pedagogy allows you to learn while building, a proven way for new skills to 'stick'.
Creator: Microsoft
Stars ⭐️: 11.1k
Forked By: 1.9k
GithubRepo: https://github.com/microsoft/Data-Science-For-Beginners
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @github_repositories_bds for more cool repositories.
*This channel belongs to @bigdataspecialist group
GitHub
GitHub - microsoft/Data-Science-For-Beginners: 10 Weeks, 20 Lessons, Data Science for All!
10 Weeks, 20 Lessons, Data Science for All! Contribute to microsoft/Data-Science-For-Beginners development by creating an account on GitHub.
Hyatt_Saleh_The_Machine_Learning_Workshop_Second_Edition_Get_ready.pdf
6.3 MB
The Machine Learning Workshop
Get ready to develop your own high-performance
machine learning algorithms with scikit-learn
Author: Hyatt Saleh
Pages: 285
Get ready to develop your own high-performance
machine learning algorithms with scikit-learn
Author: Hyatt Saleh
Pages: 285
Pandas_Cheat_Sheet.pdf
387.2 KB
THE PANDAS CHEAT SHEET
A well detailed guide to data wrangling using pandas
A well detailed guide to data wrangling using pandas
Reasons Why Data Goes Missing
Understanding the reason for the missing data in your dataset is important because it helps you determine the type of missing data and what you need to do about it. Lets get our brain to grasp this concept shall we?😁😁
Missing Completely at Random(MCAR): This is a fact that a certain missing value has nothing to do with its hypothetical value and values of other variables. eg:
You collect data on end-of-year holiday spending patterns. You survey adults on how much they spend annually on gifts for family and friends in dollar amounts.
You note that there are a few missing values in your holiday spending dataset. Some people started answering your survey but dropped out or skipped a question.
However, you note that you have data points from a wide distribution, ranging from low to high values.
Therefore, you conclude that the missing values aren’t related to any specific holiday spending amount range.
Missing at Random(MAR):This means that the propensity for a data point to be missing is unrelated to the missing data but related to some observed data. eg:
You repeat your data collection with a new group. You notice that there are more missing values for adults aged 18–25 than for other age groups.
But looking at the observed data for adults aged 18–25, you notice that the values are widely spread. It’s unlikely that the missing data are missing because of the specific values themselves.
Instead, some younger adults may be less inclined to reveal their holiday spending amounts for unrelated reasons (e.g., more protective of their privacy).
Missing Not at Random(MNAR): This is data that is neither MAR nor MCAR (i.e. the value of the variable that's missing is related to the reason it's missing). eg:
If some participants with low incomes avoid reporting their holiday spending amounts because they are low in your datast, then this is a MNAR problem
Understanding the reason for the missing data in your dataset is important because it helps you determine the type of missing data and what you need to do about it. Lets get our brain to grasp this concept shall we?😁😁
Missing Completely at Random(MCAR): This is a fact that a certain missing value has nothing to do with its hypothetical value and values of other variables. eg:
You collect data on end-of-year holiday spending patterns. You survey adults on how much they spend annually on gifts for family and friends in dollar amounts.
You note that there are a few missing values in your holiday spending dataset. Some people started answering your survey but dropped out or skipped a question.
However, you note that you have data points from a wide distribution, ranging from low to high values.
Therefore, you conclude that the missing values aren’t related to any specific holiday spending amount range.
Missing at Random(MAR):This means that the propensity for a data point to be missing is unrelated to the missing data but related to some observed data. eg:
You repeat your data collection with a new group. You notice that there are more missing values for adults aged 18–25 than for other age groups.
But looking at the observed data for adults aged 18–25, you notice that the values are widely spread. It’s unlikely that the missing data are missing because of the specific values themselves.
Instead, some younger adults may be less inclined to reveal their holiday spending amounts for unrelated reasons (e.g., more protective of their privacy).
Missing Not at Random(MNAR): This is data that is neither MAR nor MCAR (i.e. the value of the variable that's missing is related to the reason it's missing). eg:
If some participants with low incomes avoid reporting their holiday spending amounts because they are low in your datast, then this is a MNAR problem
Deep Learning free courses
Introduction to Deep Learning
🎬 10 video lesson
Duration ⏰: 1 week worth of material
🏃♂️ Self paced
📄 Notes, 👨🏫 Labs and many more
☢️ Projects, Competitions
Teacher: Alexander Amini, Ava Soleimany
Source: MIT
🔗 Course link
Practical Deep Learning For Coders
🎬 8 video lessons
📔 Book Read online
📄 Notes, 👨🏫 Labs and many more
Duration ⏰: 7 weeks long, 10 hours a week
🏃♂️ Self paced
Teacher: Jeremy Howard
Source: fast.ai
🔗 Course link
Deep Learning
by Kaggle, on youtube
🎬 13 video lesson
Duration ⏰: 2 hours worth of material
🔗 Course link
Learn Deep Learning and TensorFlow, without a Ph.D.
🎬 8 video lesson
Duration ⏰: 3 hours worth of material
🏃♂️ Self paced
📄 Notes, slides
Teacher: Martin Görner
Source: Google Cloud
🔗 Course link
Explore Deep Learning for Natural Language Processing
🎬 9 video lesson
Duration ⏰: 7-8 hours worth of material
🏃♂️ Self paced
Resource: Trailhead
🔗 Course link
Deep Learning Summer School
🎬 35 video lesson
Duration ⏰: 35+ hours
🏃♂️ Self paced
Resource: deeplearning
🔗 Course link
Deep Learning Prerequisites: The Numpy Stack in Python V2
Rating ⭐️: 4.5 out of 5
Students 👨🎓: 2230
Duration ⏰: 1hr 59min
Created by Lazy Programmer Team, Lazy Programmer Inc.
🔗 Course link
AI 101 Video Presentation
presentation given by 👨🏫: MIT’s Brandon Leshchinskiy
🔗 Presentation link
Deep Learning in Life Sciences - Spring 2021
🎬 22 video lesson
Duration ⏰: 31 hours worth of material
🏃♂️ Self paced
Teacher: Manolis Kellis
Resource: Class Central
🔗 Course link
Intro to Deep Learning
by Kaggle
Use TensorFlow and Keras to build and train neural networks for structured data.
Duration ⏰: 4 hours
🔗 Course link
Deep Learning An MIT Press book 📚
Authers: Ian Goodfellow, Yoshua Bengio and Aaron Courville
🔗 Book link
#Deep_Learning #deeplearning #dl #machinelearning
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
👉Join @bigdataspecialist for more👈
Introduction to Deep Learning
🎬 10 video lesson
Duration ⏰: 1 week worth of material
🏃♂️ Self paced
📄 Notes, 👨🏫 Labs and many more
☢️ Projects, Competitions
Teacher: Alexander Amini, Ava Soleimany
Source: MIT
🔗 Course link
Practical Deep Learning For Coders
🎬 8 video lessons
📔 Book Read online
📄 Notes, 👨🏫 Labs and many more
Duration ⏰: 7 weeks long, 10 hours a week
🏃♂️ Self paced
Teacher: Jeremy Howard
Source: fast.ai
🔗 Course link
Deep Learning
by Kaggle, on youtube
🎬 13 video lesson
Duration ⏰: 2 hours worth of material
🔗 Course link
Learn Deep Learning and TensorFlow, without a Ph.D.
🎬 8 video lesson
Duration ⏰: 3 hours worth of material
🏃♂️ Self paced
📄 Notes, slides
Teacher: Martin Görner
Source: Google Cloud
🔗 Course link
Explore Deep Learning for Natural Language Processing
🎬 9 video lesson
Duration ⏰: 7-8 hours worth of material
🏃♂️ Self paced
Resource: Trailhead
🔗 Course link
Deep Learning Summer School
🎬 35 video lesson
Duration ⏰: 35+ hours
🏃♂️ Self paced
Resource: deeplearning
🔗 Course link
Deep Learning Prerequisites: The Numpy Stack in Python V2
Rating ⭐️: 4.5 out of 5
Students 👨🎓: 2230
Duration ⏰: 1hr 59min
Created by Lazy Programmer Team, Lazy Programmer Inc.
🔗 Course link
AI 101 Video Presentation
presentation given by 👨🏫: MIT’s Brandon Leshchinskiy
🔗 Presentation link
Deep Learning in Life Sciences - Spring 2021
🎬 22 video lesson
Duration ⏰: 31 hours worth of material
🏃♂️ Self paced
Teacher: Manolis Kellis
Resource: Class Central
🔗 Course link
Intro to Deep Learning
by Kaggle
Use TensorFlow and Keras to build and train neural networks for structured data.
Duration ⏰: 4 hours
🔗 Course link
Deep Learning An MIT Press book 📚
Authers: Ian Goodfellow, Yoshua Bengio and Aaron Courville
🔗 Book link
#Deep_Learning #deeplearning #dl #machinelearning
➖➖➖➖➖➖➖➖➖➖➖➖➖➖
👉Join @bigdataspecialist for more👈
MIT Deep Learning 6.S191
MIT's introductory course on deep learning methods and applications
COMMON HYPOTHESIS TEST.pdf
5.2 MB
A GUIDE TO UNDERSTANDING HYPOTHESIS TEST
Tutorial-Math-Deep-Learning-2018.pdf
36.9 MB
A Guide to Understanding Mathematics for Deep Learning
Amazing Free Resources on Data Science and Machine Learning for Beginners
1) Data Science for Beginners - A Curriculum
By: Azure Cloud Advocates at Microsoft
Stars ⭐️: 15K
Fork: 2.4K
Repo: https://microsoft.github.io/Data-Science-For-Beginners/#/?id=lessons
2) Machine Learning for Beginners - A Curriculum
By: Azure Cloud Advocates at Microsoft
Stars ⭐️: 38K
Fork: 7.4K
Repo: https://microsoft.github.io/ML-For-Beginners/#/
1) Data Science for Beginners - A Curriculum
By: Azure Cloud Advocates at Microsoft
Stars ⭐️: 15K
Fork: 2.4K
Repo: https://microsoft.github.io/Data-Science-For-Beginners/#/?id=lessons
2) Machine Learning for Beginners - A Curriculum
By: Azure Cloud Advocates at Microsoft
Stars ⭐️: 38K
Fork: 7.4K
Repo: https://microsoft.github.io/ML-For-Beginners/#/
microsoft.github.io
Data Science for Beginners
Description
Head First SQL
Here's a brain friendly guide to learning SQL for beginners
Author:Lynn Beighley
Pages: 586
Link: Click Me!
Here's a brain friendly guide to learning SQL for beginners
Author:Lynn Beighley
Pages: 586
Link: Click Me!
Statistics Guide for Data Science
Learning Statistics for Data Science can be quite overwhelming for beginners without a Statistics background. One can get confused on which topics to learn or books to read up to equip their knowledge
You don't have to learn it all. Here are essential topics you can learn
1) Know what a p value is and its limitations
2) Linear Regression and its Assumptions
3) Different Statistical Distributions and when to use them
4) Mean, Variance for Normal, Poisson, and Uniform Distribution
5) Sampling Techniques and Common Designs(eg: A/B)
6) Bayes Theorems and it's application
7) Measurements and Interpretation of Confidence Intervals
8) Logistics Regressions and ROC curves
9) Resampling(Cross Validation and Bootstrapping)
10) Tree Based Models
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group
Learning Statistics for Data Science can be quite overwhelming for beginners without a Statistics background. One can get confused on which topics to learn or books to read up to equip their knowledge
You don't have to learn it all. Here are essential topics you can learn
1) Know what a p value is and its limitations
2) Linear Regression and its Assumptions
3) Different Statistical Distributions and when to use them
4) Mean, Variance for Normal, Poisson, and Uniform Distribution
5) Sampling Techniques and Common Designs(eg: A/B)
6) Bayes Theorems and it's application
7) Measurements and Interpretation of Confidence Intervals
8) Logistics Regressions and ROC curves
9) Resampling(Cross Validation and Bootstrapping)
10) Tree Based Models
➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖➖
Join @datascience_bds for more cool data science materials.
*This channel belongs to @bigdataspecialist group