How to avoid machine learning pitfalls.pdf
268.5 KB
How to avoid machine learning pitfalls
git-cheat-sheet-education.pdf
97.8 KB
GitHub basic commands
Learn Generative AI | Machine Learning | Deep learning | Artificial Intelligence - Material, Books, Videos, Exercises via @like
Gist of the above article:
Building successful ML-based software projects is still difficult because every ML-based software needs to manage three main assets: Data, Model, and Code
—————————————
Machine Learning Operations(= MLOps) --> processes around designing, building, and deploying ML models into production.
Mainly 3 Steps:
1.Data —> Data Engineering Pipelines
2.Model —> Machine Learning Pipelines
3.Code —> Deployment Pipelines
———————————-
1.Data: Data Engineering Pipelines
1A: Data Ingestion
-Collecting data by using various systems
1B:Exploration and Validation
-Understanding the data
-obtain information about the content and structure of the data.
1C:Data Wrangling (Cleaning)
1D:Data Splitting
-Splitting the data into training (80 %), validation, and test datasets
————————————
2.Model: Machine Learning Pipelines
2A: Model Training
2B: Model Evaluation
2C: Model Testing
2D: Model Packaging
———————————-
3.Code: Deployment Pipelines
3A:Model Serving -
Deploying the ML model in a production environment.
3B: Model Performance Monitoring - The process of observing the ML model performance based on live and previously unseen data, such as prediction or recommendation.
3C:Model Performance Logging - Every inference request results in a log-record.
At Last:
Deploying ML Models as Docker Containers
(Please read main article, I have not covered all things.It is very extensive. You will find this article useful when you will start hand-on-experience)
Building successful ML-based software projects is still difficult because every ML-based software needs to manage three main assets: Data, Model, and Code
—————————————
Machine Learning Operations(= MLOps) --> processes around designing, building, and deploying ML models into production.
Mainly 3 Steps:
1.Data —> Data Engineering Pipelines
2.Model —> Machine Learning Pipelines
3.Code —> Deployment Pipelines
———————————-
1.Data: Data Engineering Pipelines
1A: Data Ingestion
-Collecting data by using various systems
1B:Exploration and Validation
-Understanding the data
-obtain information about the content and structure of the data.
1C:Data Wrangling (Cleaning)
1D:Data Splitting
-Splitting the data into training (80 %), validation, and test datasets
————————————
2.Model: Machine Learning Pipelines
2A: Model Training
2B: Model Evaluation
2C: Model Testing
2D: Model Packaging
———————————-
3.Code: Deployment Pipelines
3A:Model Serving -
Deploying the ML model in a production environment.
3B: Model Performance Monitoring - The process of observing the ML model performance based on live and previously unseen data, such as prediction or recommendation.
3C:Model Performance Logging - Every inference request results in a log-record.
At Last:
Deploying ML Models as Docker Containers
(Please read main article, I have not covered all things.It is very extensive. You will find this article useful when you will start hand-on-experience)
Internship Alert:
If you have basic knowledge of computer vision, I'm looking for interns at Doctor on Click Pvt Ltd.
(Image manipulation/ Images masking/ Image segmentation/ Image classifications. Anything)
Check out this job at Doctor On Click: https://www.linkedin.com/jobs/view/2721296401
If you have basic knowledge of computer vision, I'm looking for interns at Doctor on Click Pvt Ltd.
(Image manipulation/ Images masking/ Image segmentation/ Image classifications. Anything)
Check out this job at Doctor On Click: https://www.linkedin.com/jobs/view/2721296401
Linkedin
Doctor On Click hiring Machine Learning Intern in India | LinkedIn
Posted 7:42:28 PM. Company : Doctor on Click Pvt. Ltd.Position : Machine Learning internDuration : 3 months / 6…See this and similar jobs on LinkedIn.
--------------------------
Big Tech & Their Favourite Deep Learning Techniques
--------------------------
https://analyticsindiamag.com/big-tech-their-favourite-deep-learning-techniques/
Big Tech & Their Favourite Deep Learning Techniques
--------------------------
https://analyticsindiamag.com/big-tech-their-favourite-deep-learning-techniques/
Analytics India Magazine
Big Tech & Their Favourite Deep Learning Techniques
Every week, the top AI labs globally -- Google, Facebook, Microsoft, Apple, etc. -- release tons of new research work, tools, datasets, models, libraries and frameworks in artificial intelligence (AI) and machine learning (ML).
Learn Generative AI | Machine Learning | Deep learning | Artificial Intelligence - Material, Books, Videos, Exercises via @like
Machine learning Crash course By Google
https://developers.google.com/machine-learning/crash-course
https://developers.google.com/machine-learning/crash-course
❤1
👆It is free. Open for all.
What type of content are you expecting from this channel? (You can select multiple options, all your interests)
Anonymous Poll
37%
Data science related
56%
Machine learning (classical)
49%
Deep learning / Neural network frameworks
44%
Videos content
57%
Books/PDFs
16%
Important blogs
👍1
Hands_On_Machine_Learning_with_Scikit_Learn_Keras_and_Tensorflow.pdf
31.5 MB
One of the most requested Book for Machine learning. Save for the future reference and doubt solving.
Harvard - Resumes & Cover Letters guide.pdf
1.4 MB
Also includes list of Verbs and samples
very easy to understand and good book
👍1
I'm hiring for Django Developer (Intern and/or Full time Developer)