Adapters: A Compact and Extensible Transfer Learning Method for NLP
____
@Machine_learn
___
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
____
@Machine_learn
___
https://medium.com/dair-ai/adapters-a-compact-and-extensible-transfer-learning-method-for-nlp-6d18c2399f62
Medium
Adapters: A Compact and Extensible Transfer Learning Method for NLP
Adapters obtain comparable results to BERT on several NLP tasks while achieving parameter efficiency.
آدرس وب سایت هاس خارجی ارایه دهنده کورس های آموزشی دیتاساینس:
eu.udacity.com
www.coursera.org
www.datacamp.com
www.udemy.com
آدرس موسسات ایرانی ارایه دهنده آموزش های دیتاساینس :
www.tihe.ac.ir
faradars.org
وب سایتی که کورس ها رو بصورت رایگان گذاشته:
bitdownload.ir
#Data_science
@Machine_learn
eu.udacity.com
www.coursera.org
www.datacamp.com
www.udemy.com
آدرس موسسات ایرانی ارایه دهنده آموزش های دیتاساینس :
www.tihe.ac.ir
faradars.org
وب سایتی که کورس ها رو بصورت رایگان گذاشته:
bitdownload.ir
#Data_science
@Machine_learn
@Machine_learn
#paper #video
We Can All Become Video Game Characters With This AI
Video: https://www.youtube.com/watch?v=Y73iUAh56iI
Paper: https://arxiv.org/abs/1904.08379
#paper #video
We Can All Become Video Game Characters With This AI
Video: https://www.youtube.com/watch?v=Y73iUAh56iI
Paper: https://arxiv.org/abs/1904.08379
Handling imbalanced datasets in
machine learning
What should and should not be done when facing an imbalanced classes problem?
#report #ML
@Machine_learn
machine learning
What should and should not be done when facing an imbalanced classes problem?
#report #ML
@Machine_learn
Forwarded from Ramin Mousa
4_6021699893096089510.pdf
1.1 MB
Handling imbalanced datasets in
machine learning
What should and should not be done when facing an imbalanced classes problem?
#report #ML
@Machine_learn
machine learning
What should and should not be done when facing an imbalanced classes problem?
#report #ML
@Machine_learn
@Machine_learn
10 Python image manipulation tools.
An overview of some of the commonly used Python libraries that provide an easy and intuitive way to transform images.
https://towardsdatascience.com/image-manipulation-tools-for-python-6eb0908ed61f
10 Python image manipulation tools.
An overview of some of the commonly used Python libraries that provide an easy and intuitive way to transform images.
https://towardsdatascience.com/image-manipulation-tools-for-python-6eb0908ed61f
Medium
10 Python image manipulation tools.
An overview of some of the commonly used Python libraries that provide an easy and intuitive way to transform images.
Deep Learning Illustrated
A Visual, Interactive Guide to Artificial
Intelligence, First Editon
#book #DL #CNN #RNN
@Machine_learn
A Visual, Interactive Guide to Artificial
Intelligence, First Editon
#book #DL #CNN #RNN
@Machine_learn
4_5812241008154379716.pdf
11.8 MB
Deep Learning Illustrated
A Visual, Interactive Guide to Artificial
Intelligence, First Editon
#book #DL #CNN #RNN
@Machine_learn
A Visual, Interactive Guide to Artificial
Intelligence, First Editon
#book #DL #CNN #RNN
@Machine_learn
@Machine_learn
Course Curriculm #course
#ML
1. Welcome to the Applied Machine Learning Course
2. Introduction to Data Science and Machine Learning
3. Introduction to the Course
4. Setting up your system
5. Python for Data Science
6. Statistics For Data Science
7. Basics Steps of Machine Learning and EDA
8. Data Manipulation and Visualization
9. Project: EDA - Customer Churn Analysis
10. Share your Learnings
11. Build Your First Predictive Model
12. Evaluation Metrics
13. Build Your First ML Model: k-NN
14. Selecting the Right Model
15. Linear Models
16. Project: Customer Churn Prediction
17. Dimensionality Reduction (Part I)
18. Decision Tree
19. Feature Engineering
20. Share your Learnings
21. Project: NYC Taxi Trip Duration prediction
22. Working with Text Data
23. Naïve Bayes
24. Multiclass and Multilabel
25. Project: Web Page Classification
26. Basics of Ensemble Techniques
27. Advance Ensemble Techniques
28. Project: Ensemble Model on NYC Taxi Trip Duration Prediction
29. Share your Learnings
30. Advance Dimensionality Reduction
31. Support Vector Machine
32. Unsupervised Machine Learning Methods
33 AutoML and Dask
34. Neural Network
35. Model Deployment
36. Interpretability of Machine Learning Models
.https://courses.analyticsvidhya.com/courses/applied-machine-learning-beginner-to-professional?utm_source=sendinblue&utm_campaign=July_Newsletter_2019&utm_medium=email
Course Curriculm #course
#ML
1. Welcome to the Applied Machine Learning Course
2. Introduction to Data Science and Machine Learning
3. Introduction to the Course
4. Setting up your system
5. Python for Data Science
6. Statistics For Data Science
7. Basics Steps of Machine Learning and EDA
8. Data Manipulation and Visualization
9. Project: EDA - Customer Churn Analysis
10. Share your Learnings
11. Build Your First Predictive Model
12. Evaluation Metrics
13. Build Your First ML Model: k-NN
14. Selecting the Right Model
15. Linear Models
16. Project: Customer Churn Prediction
17. Dimensionality Reduction (Part I)
18. Decision Tree
19. Feature Engineering
20. Share your Learnings
21. Project: NYC Taxi Trip Duration prediction
22. Working with Text Data
23. Naïve Bayes
24. Multiclass and Multilabel
25. Project: Web Page Classification
26. Basics of Ensemble Techniques
27. Advance Ensemble Techniques
28. Project: Ensemble Model on NYC Taxi Trip Duration Prediction
29. Share your Learnings
30. Advance Dimensionality Reduction
31. Support Vector Machine
32. Unsupervised Machine Learning Methods
33 AutoML and Dask
34. Neural Network
35. Model Deployment
36. Interpretability of Machine Learning Models
.https://courses.analyticsvidhya.com/courses/applied-machine-learning-beginner-to-professional?utm_source=sendinblue&utm_campaign=July_Newsletter_2019&utm_medium=email
🖇 @Machine_learn
Facebook is open-sourcing DLRM — a state-of-the-art deep learning recommendation model to help AI researchers and the systems and hardware community develop new, more efficient ways to work with categorical data.
fb: https://ai.facebook.com/blog/dlrm-an-advanced-open-source-deep-learning-recommendation-model/
link: https://arxiv.org/abs/1906.03109
Facebook is open-sourcing DLRM — a state-of-the-art deep learning recommendation model to help AI researchers and the systems and hardware community develop new, more efficient ways to work with categorical data.
fb: https://ai.facebook.com/blog/dlrm-an-advanced-open-source-deep-learning-recommendation-model/
link: https://arxiv.org/abs/1906.03109
Meta
We are open-sourcing a state-of-the-art deep learning recommendation model to help AI researchers and the systems and hardware…
Deep learning with Python Develop Deep Learning models on Theano and Thensorflow using Keras
#book #keras #DL
@Machine_learn
#book #keras #DL
@Machine_learn
5_6133943928459624650.pdf
5.4 MB
Deep learning with Python Develop Deep Learning models on Theano and Thensorflow using Keras
#book #keras #DL
@Machine_learn
#book #keras #DL
@Machine_learn