![ReproRehab Profile](https://pbs.twimg.com/profile_images/1534426723432878081/QSHYrIZD_x96.jpg)
ReproRehab
@reprorehab
Followers
170
Following
75
Statuses
248
Bringing data science into rehabilitation research.
Joined March 2022
An interesting discussion of how to navigate secondary data collection and use
Save The Date for a #LoveDataWeek25 webinar from #sbeccc: "Making Others' Data Your Own: Adding Value and Promoting Interoperability through Secondary Data Collection and Use" on Monday, February 10 from 1-2 pm ET. Register here:
0
0
2
An awesome opportunity to learn from each other!
#ACRM2025 Call for Proposals Wave 1 Closes 30 Jan Big benefits to submitting your proposal now Looking for symposium, instructional course, scientific paper or poster LaunchPad applications open too Go to #rehabilitation #neurorehabilitation #physiatry
0
0
0
An interesting read on the use of technology and data in the rehabilitation setting!
Now in #ARRCT the #ACRM #openaccess journal Use of technology in the rehabilitation setting: therapy observations, mixed methods analysis, and data visualization. At #technology #rehabilitation #occupationaltherapy #physicaltherapy #physiatry
0
0
0
RT @NIHDataScience: π Curious about the latest in #DataScience and #AI in biomedical research? Read about Dr. Susan Gregurick's insightfulβ¦
0
3
0
RT @ASNRehab: π¨ Reminder! Applications for our #Diversity Travel Fellowship are due Feb. 7th! This program provides travel support, complimβ¦
0
1
0
RT @ASNRehab: π’ Reminder! Applications are open for our Virtual Mentoring Program! Not sure what to expect? Check out @BP_neurosci's virtuβ¦
0
2
0
check this out!
SOTA RAG Systems Today Over the last year, RAG has evolved dramatically, and most SOTA systems today support - Multi-modal documents and responses - LLM routing to different LLMs based on the complexity of the query - Multi-lingual requests and response - Increased accuracy and reduced hallucination with verification steps - Feedback and monitoring of the system in production A clever approach was proposed recently called Speculative RAG. This framework leverages a larger generalist LM to efficiently verify multiple RAG drafts produced in parallel by a smaller, distilled specialist LM. Each draft is generated from a distinct subset of retrieved documents, offering diverse perspectives on the evidence while reducing input token counts per draft. This approach enhances comprehension of each subset and mitigates potential position bias over an extended context. Their method accelerates RAG by delegating drafting to the smaller specialist LM, with the larger generalist LM performing a single verification pass over the drafts. Speculative RAG enhances accuracy by up to 12.97% while reducing latency by 51% compared to conventional RAG systems on PubHealth. Approaches like this have helped solve complex RAG problems.
0
0
1
RT @ACRMStroke: Join the worldβs largest interdisciplinary #rehabilitation #research event at #ACRM2024 The WHOLE rehabilitation team is weβ¦
0
1
0
π€
Become a Data Analyst (Without the Mystery!) #DataAnalyst #python #programming #developer #programmer #coding #coder #softwaredeveloper #computerscience #pythonprogramming #ai #ml #machinelearning #datascience #excel #sql #math #maths #mathematics
1
0
1
RT @ASNRehab: Already starting to think about your conference schedule for next year? Make sure to mark your calendar for April 23-25, andβ¦
0
5
0
RT @AOTFoundation: Join us for #OTResearch Education, Networking, and Fun! Register for the inaugural #AOTAEngageSummit where community parβ¦
0
2
0
nice resource!
Free Certification Courses to Learn Machine Learning in 2024: 1. Python π 2. SQL π 3. Statistics and R π 4. Data Science: R Basics π 5. Excel and PowerBI π 6. Data Science: Visualization π 7. Data Science: Machine Learning π 8. R π 9. Tableau π 10. PowerBI π 11. Data Science: Productivity Tools π 12. Data Science: Probability π 13. Mathematics π 14. Statistics π 15. Data Visualization π 16. Machine Learning π 17. Deep Learning π 18. Data Science: Linear Regression π 19. Data Science: Wrangling π 20. Linear Algebra π 21. Probability π 22. Introduction to Linear Models and Matrix Algebra π 23. Data Science: Capstone π 24. Data Analysis π 25. IBM Data Science Professional Certificate 26. Neural Networks and Deep Learning 27. Supervised Machine Learning: Regression and Classification Happy Learning!π Follow @dev_manishshah for more such content.
0
0
2