Yep exactly! 🙂 The first time I saw the Exemplar SVM idea. It's so simple but also a bit counter-intuitive, I think because low dimensional intuition fails us. A classifier with a single example? In low dimensions it sounds weird. In high dimensions it works great.
RESEARCH
-
Customizing Embeddings and Comparing Distance Metrics in AI
By
–
Nice — curious how this compares to learning a modified distance metric as shown here: https://
github.com/openai/openai-
cookbook/blob/main/examples/Customizing_embeddings.ipynb
… -
SVMs Outperform k-Nearest Neighbor for Embedding Lookups
By
–
Random note on k-Nearest Neighbor lookups on embeddings: in my experience much better results can be obtained by training SVMs instead. Not too widely known. Short example: https://
github.com/karpathy/rando
mfun/blob/master/knn_vs_svm.ipynb
… Works because SVM ranking considers the unique aspects of your query w.r.t. data. -
ControlNet v1.1 Released: Canny, OpenPose Plus 12 Checkpoints
By
–
The amazing @lvminzhang has open-sourced the next version of ControlNet – Canny v1.1
– Open-pose v1.1
– & 12 others new checkpoints You can find theDiffusers' checkpoints here: https://
huggingface.co/models?sort=do
wnloads&search=lllyasvielcontrol_v11
… -
Tactile Diffusion: Bridging Sim2Real Gap in Tactile Sensing
By
–
Tactile Diffusion generates synthetic tactile images from sim data, capturing the complex illumination of the gel deformation. This research from UW & Meta AI is the first method using diffusion to close the sim2real gap for vision-based tactile sensing.
— AI at Meta (@AIatMeta) 14 avril 2023
Read the paper ⬇️Tactile Diffusion generates synthetic tactile images from sim data, capturing the complex illumination of the gel deformation. This research from UW & Meta AI is the first method using diffusion to close the sim2real gap for vision-based tactile sensing. Read the paper
-
Google Quantum AI Celebrates World Quantum Day Education
By
–
We’re excited to celebrate this #WorldQuantumDay by helping anyone understand & contribute to quantum computing — and supporting the education of the next generation of quantum technologists. Read all about it on this blog from the @GoogleQuantumAI team ↓
-
Cost of Generative AI and Nano-Excitonic Transistor Breakthrough
By
–
Right now everybody is talking about use of Generative AI, very soon, it will be about the cost of doing that – this is very promising: Team develops the world's smallest and fastest nano-excitonic transistor https://
flip.it/dOfKVC -
Automatic Differentiation Bounds Improve ML Training Learning Rates
By
–
A new generalization of automatic differentiation lets researchers compute upper and lower bounds on functions, instead of just derivatives, leading toward more principled learning rate selection during #ML model training. Learn more: https://
goo.gle/417iphD -
How Not to Destroy the World with AI: Stuart Russell’s Critical Lecture
By
–
Thought-provoking and timely lecture by Prof. Stuart Russell, co-author of the most popular AI textbook in the world, on "How Not to Destroy the World with AI":
-
Recent AI Hype Cycle Recognized as Overhyped, Not Transformative
By
–
A rather recent AI hype cycle is pretty much agreed to have been that, rather than a transformation of society. https://
wsj.com/articles/cars-
self-driving-when-c6ae4fdc
… (you can read my analyses and predictions from 2017&2018 at http://
rodneybrooks.com/blog).