A quick experiment that took a bit due to kNN scaling on large datasets: the kNN + Gzip method is a bit better than cosine similarity on count vectors. On the IMDb Movie review dataset:
– 70% test acc for gzip
– 65% test acc for cosine distance My (re)implementation code:
CODE
-
kNN Gzip Method Outperforms Cosine Similarity on IMDb Reviews
By
–
-
GenAI Meetup: Open Source LLMs and AI Frameworks
By
–
@malai_san & @saamatechinc team is hosting a #GenAI meetup this weekend (29th June – 10 AM) in #Chennai. ⦿ Adapting Open Source LLMS for your Use Case – Logesh Kumar
⦿ Empowering AI applications using LLAMAINDEX and LANGCHAIN – Praveen R & R Dhilip -
Ship Small Software Projects to Learn Without Bias
By
–
I think shipping small software projects without worrying about the outcome is a good way to learn honestly without being biased. Conviction should be developed and trailed by fire rather than something you wake up with one day. You test, and if something fails, then so be it.
-
Learning New Fields Through Shipping Small Projects
By
–
the only way I learn about a new field is by shipping small projects and testing the waters. It’s fun!
-
Stytch Auth Workshop at Hack Night Event
By
–
Kicking off the Hack Night with @stytchauth A workshop presented by @CalRueb
-
Stanford CS224W: Machine Learning with Graphs on YouTube
By
–
(1) Stanford CS224W: Machine Learning with Graphs – YouTube
https://bit.ly/3wPe1nR #AI #MachineLearning #DeepLearning #LLMs #DataScience -
Senior Leadership Team Approval Process for Product Decisions
By
–
Then it comes up to the senior leadership team (SLT), which they call OK2, which includes, again, product, UX, engineering, and data, who all have to sign off on it as well.
-
LangSmith traces visualization and monitoring techniques
By
–
What do the traces on langsmith for this look like?
-
Fine-tuned Open-Source LLMs Integration with LangChain and Predibase
By
–
Use #finetuned open-source #LLMs with @langchain and @Predibase Excited to share our new integration which makes it easier than ever before to deploy, customize and chain LLMs on your own #data! https://
python.langchain.com/docs/integrati
ons/llms/predibase
…