Today on the blog, read all about how we use a hierarchical partitioning procedure to build an efficient differentially private algorithm for computing heatmaps with provable guarantees #DifferentialPrivacy → https://
goo.gle/3MV5zyT
MACHINE LEARNING
-
Hierarchical Partitioning for Differentially Private Heatmap Computation
By
–
-
Pen and Paper Exercises in Machine Learning: Foundational Topics
By
–
Pen and Paper Exercises in Machine Learning A handy collection of pen-and-paper exercises in machine learning. Covers foundational topics related to machine learning such as linear algebra, optimization, graphical models and etc… This is a relevant resource for anyone who
-
Microsoft SPTAG: Distributed Vector Search Library for Large Scale
By
–
Bing Vector Search GitHub – microsoft/SPTAG: A distributed approximate nearest neighborhood search (ANN) library which provides a high quality vector index build, search and distributed online serving toolkits for large scale vector search scenario. https://
bit.ly/3LbJef8 -
Unpredictable Performance Spikes in Scaling Neural Networks
By
–
I think this is a reasonable point in theory. In practice, we don't have those model sizes. But assuming that we did, I think there's still something interesting going on with emergence, e.g., "We can't predict a performance spike at say 10B with models from 5B, 4.9B, 4.8B…"
-
Discussion on Prompt Engineering, RLHF, AI Safety, and AGI
By
–
Got to chat about prompt engineering, RLHF, LLM red teaming, AI safety, and AGI with @labenz on the @CogRev_Podcast — thanks so much for having me, Nathan!
-
DataRobot AI Platform 9.0 Enables Seamless ML Collaboration
By
–
When teams have a way to work together, it amplifies productivity and makes it easier to iterate and experiment. Find out how the DataRobot AI Platform 9.0 allows seamless collaboration, helping derive the most value from #ML. Read more: https://
bit.ly/3UQcefB -
Efficient finetuning concept parallel discussion
By
–
yeah that's an interesting parallel, seems like a similar concept to an efficient form of finetuning
-
Join GenerationAI: Build, Train, Deploy LLMs at DataAISummit
By
–
Welcome to #GenerationAI Whether you’re an engineering wizard, ML pro, SQL expert — or you want to learn how to build, train and deploy #LLMs — you’ll be in good company at #DataAISummit. Register now! https://
bit.ly/3ICPryg -
Neuromorphic Computing Future: SNNs with Transformers and RL
By
–
The future will be resource efficient spiking neural networks also known as neuromorphic computing with Transformers, RL & neurosymbolic architecture embedded into it.
-
Digital Ready Skills: RPA and Machine Learning Office Hours
By
–
RU #DigitalReady?? #RPA, #machinelearning – they're on the test! Come to office hours so you're prepared. @KMcCormickBlog is a legend. And, I know a legend. So, you'll want to join both of us as we discuss our LinkedIn Learning courses, and the skills…lnkd.in/eUQAMkcd