đ Marque-pages Pinboard
â Retour Ă tous les marque-pages443 rĂ©sultats (251-443 marque-pages affichĂ©s)
github.com
FauxPilot - an open-source GitHub Copilot server. Contribute to moyix/fauxpilot development by creating an account on GitHub.
www.looker.com
Looker is a business intelligence software and big data analytics platform that helps you explore, analyze and share real-time business analytics easily.
arc.tencent.com
www.topazlabs.com
Improve image resolution with deep learning. Join hundreds of thousands of photographers who use Gigapixel AI for printing, cropping, restoration, and more.
dallery.gallery
github.com
Image Super-Resolution for Anime-Style Art. Contribute to nagadomi/waifu2x development by creating an account on GitHub.
github.com
Image Upscaling GUI based on ESRGAN. Contribute to n00mkrad/cupscale development by creating an account on GitHub.
www.biped.ai
biped is a smart harness that uses self-driving technology to guide blind and partially-sighted people with 3D sounds. Avoid obstacles and navigate safely.
www.wombo.art
Create beautiful artwork using the power of AI! Enter a prompt, pick an art style and watch WOMBO Dream turn your idea into an AI-powered painting in seconds.
github.com
LexNLP by LexPredict. Contribute to LexPredict/lexpredict-lexnlp development by creating an account on GitHub.
causal.app
Causal replaces your spreadsheets with a better way to build models, connect to data (accounting, CRM), and share dashboards with your team. Sign up for free.
open-meteo.com
www.dask.org
Dask is a flexible open-source Python library for parallel computing maintained by OSS contributors across dozens of companies including Anaconda, Coiled, SaturnCloud, and nvidia.
www.raspberrypi.com
github.com
Documentation for GitHub Copilot. Contribute to github/copilot-docs development by creating an account on GitHub.
github.com
GitHub Copilot works alongside you directly in your editor, suggesting whole lines or entire functions for you.
github.com
Contribute to kuprel/min-dalle development by creating an account on GitHub.
github.com
A playground to generate images from any text prompt using DALL-E Mini and based on OpenAI's DALL-E https://openai.com/blog/dall-e/ - saharmor/dalle-playground: A playground to generate images from any text prompt using DALL-E Mini and based on OpenAI's DALL-E https://openai.com/blog/dall-e/
github.com
Pretrained language model with 100B parameters. Contribute to yandex/YaLM-100B development by creating an account on GitHub.
replika.com
Always here to listen and talk. Always on your side. Join the millions growing with their AI friends now!
github.com
Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple - snakers4/silero-models: Silero Models: pre-trained speech-to-text, text-to-speech and text-enhancement models made embarrassingly simple
openhands.ai4bharat.org
delta-academy.xyz
Learn reinforcement learning in 4 weeks through games, not lectures. Every week, build an AI which battles to be crowned champion of the cohort in a live competition.
waitbutwhy.com
Part 1 of 2: "The Road to Superintelligence". Artificial Intelligence â the topic everyone in the world should be talking about.
www.tensorflow.org
www.youtube.com
For more information about Stanfordâs Artificial Intelligence professional and graduate programs, visit: https://stanford.io/aiAssistant Professor Chelsea Fi...
imagen.research.google
databricks.com
Databricks combines data warehouses & data lakes into a lakehouse architecture. Collaborate on all of your data, analytics & AI workloads using one platform.
github.com
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch - lucidrains/DALLE2-pytorch: Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
paglen.studio
www.eleuther.ai
gradio.app
andrewmayneblog.wordpress.com
www.ai21.com
www.baseten.co
laion.ai
celody.com
clipasso.github.io
www.jpohhhh.com
pollinations.ai
openai.com
blog.nelhage.com
www.impira.com
codeplea.com
www.slai.io
ai.facebook.com
lifeminetx.com
openai.com
distill.pub
www.youtube.com
arxiv.org
We demonstrate that a neural network pre-trained on text and fine-tuned on code solves Mathematics problems by program synthesis. We turn questions into programming tasks, automatically generate programs, and then execute them, perfectly solving university-level problems from MIT's large Mathematics courses (Single Variable Calculus 18.01, Multivariable Calculus 18.02, Differential Equations 18.03, Introduction to Probability and Statistics 18.05, Linear Algebra 18.06, and Mathematics for Computer Science 6.042), Columbia University's COMS3251 Computational Linear Algebra course, as well as questions from a MATH dataset (on Prealgebra, Algebra, Counting and Probability, Number Theory, and Precalculus), the latest benchmark of advanced mathematics problems specifically designed to assess mathematical reasoning. We explore prompt generation methods that enable Transformers to generate question solving programs for these subjects, including solutions with plots. We generate correct answers for a random sample of questions in each topic. We quantify the gap between the original and transformed questions and perform a survey to evaluate the quality and difficulty of generated questions. This is the first work to automatically solve, grade, and generate university-level Mathematics course questions at scale. This represents a milestone for higher education.
blogs.nvidia.com
arxiv.org
Dimension reduction (DR) techniques such as t-SNE, UMAP, and TriMAP have demonstrated impressive visualization performance on many real world datasets. One tension that has always faced these methods is the trade-off between preservation of global structure and preservation of local structure: these methods can either handle one or the other, but not both. In this work, our main goal is to understand what aspects of DR methods are important for preserving both local and global structure: it is difficult to design a better method without a true understanding of the choices we make in our algorithms and their empirical impact on the lower-dimensional embeddings they produce. Towards the goal of local structure preservation, we provide several useful design principles for DR loss functions based on our new understanding of the mechanisms behind successful DR methods. Towards the goal of global structure preservation, our analysis illuminates that the choice of which components to preserve is important. We leverage these insights to design a new algorithm for DR, called Pairwise Controlled Manifold Approximation Projection (PaCMAP), which preserves both local and global structure. Our work provides several unexpected insights into what design choices both to make and avoid when constructing DR algorithms.
ermongroup.github.io
pollinations.ai
thissneakerdoesnotexist.com
researchai.co
hdbscan.readthedocs.io
umap-learn.readthedocs.io
umap-learn.readthedocs.io
umap-learn.readthedocs.io
umap-learn.readthedocs.io
scikit-learn.org
dawndrain.github.io
romain-hennequin.fr
research.google
pair-code.github.io
en.wikipedia.org
sh-tsang.medium.com
hdbscan.readthedocs.io
www.quasimondo.com
www.xavierdupre.fr
fr.wikipedia.org
rapids.ai
karpathy.ai
fr.wikipedia.org
peltarion.com
lilianweng.github.io
kuleshov.github.io
www.youtube.com
driesdepoorter.be
nvidia-research-mingyuliu.com
One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing
socialcdt.org
fr.wikipedia.org
zama.ai
github.com
atcold.github.io
github.com
johnhw.github.io
This is the first million integers, represented as binary vectors indicating their prime factors, and laid out using the UMAP dimensionality reduction algorithm by Leland McInnes. Each integer is represented in a high-dimensional space, and gets squished down to 2D so that numbers with similar prime factorisations are closer together than those with dissimilar factorisations.
towardsdatascience.com
stats.stackexchange.com
emojify.info
www.cs.toronto.edu
snap.stanford.edu
louismartin.eu
www.deeplearning.ai
imagine.enpc.fr
nvlabs.github.io
paperswithcode.com
paperswithcode.com
www.chessprogramming.org
www.cs.cornell.edu
openai.com
www.thismusicvideodoesnotexist.com
www.pyimagesearch.com
experiments.withgoogle.com
dataflowr.github.io
towardsdatascience.com
en.wikipedia.org
medium.com
nsfw-categorize.it
www.myheritage.fr
cedric.cnam.fr
cs229.stanford.edu
www.cs.cornell.edu
dvl.in.tum.de
www.youtube.com
fr.wikipedia.org
developers.google.com
aws.amazon.com
www.fast.ai
playground.tensorflow.org
cs231n.github.io
www.deeplearningbook.org
machinelearningmastery.com
machinelearningmastery.com
adeshpande3.github.io
fr.wikipedia.org
en.wikipedia.org
fr.wikipedia.org
cp4space.hatsya.com
towardsdatascience.com
neuralnetworksanddeeplearning.com
naiveHobo/InvoiceNet: Deep neural network to extract intelligent information from invoice documents.
github.com
fr.wikipedia.org
github.com
www.kaggle.com
naokishibuya.medium.com
machinelearningmastery.com
fr.wikipedia.org
en.wikipedia.org
machinelearningmastery.com
machinelearningmastery.com
towardsdatascience.com
towardsdatascience.com
towardsdatascience.com
fr.wikipedia.org
fr.wikipedia.org
fr.wikipedia.org
fr.wikipedia.org
en.wikipedia.org
www.youtube.com
huggingface.co
Build, train and deploy state of the art models powered by the reference open source in natural language processing.
marksaroufim.substack.com
towardsdatascience.com
research.google
nn.labml.ai
fr.wikipedia.org