Hamid

[Alireza.js🇮🇷 @alihd_js]

اگر هنوز نمیدونی چجوری از Codex استفاده کنی، یه آموزش جامع و کوتاه اوردم واستون که:

توی پارت اول: بیسیک هایCodex رو میگه.

پارت دوم: باهاش یاد میگیرید چجوری یه اپ یا پلتفرم بسازید بصورت کاملا عملی.

از دستش ندید 🍻 خیلی خوبه.

[Mike Tamir, PhD @MikeTamir]

How diffusion models work: the math from scratch | AI Summer https://t.co/ak0UiJXdKC
#AI #DeepLearning #MachineLearning #DataScience

[Andrej Karpathy @karpathy]

🥷New (1h55m) Lecture #5: "Becoming a Backprop Ninja" https://t.co/ekZgAQON3O
We take the 2-layer MLP from last lecture and backprop through all of it manually: cross entropy loss, linear layer 2, tanh, batchnorm, linear layer 1, embedding table. I give away answers in the video

[Big Data Analytics News @BDAnalyticsnews]

Machine learning models cheat sheet

#ArtificialIntelligence #AI #ML #DataScience #DataScientists #CodeNewbies #Tech #deeplearning #CyberSecurity #Python #Coding #javascript #rstats #100DaysOfCode #programming #Linux #IoT #IIoT #BigData

[Jean de Nyandwi @Jeande_d]

Operationalizing Machine Learning: An Interview Study

18 interviews with ML engineers on the best practices and challenges for deploying machine learning models in production.

This is a recommended read for people in MLOps. Well-written.

https://t.co/4hpR8190vr

[AK @_akhaliq]

Understanding Scaling Laws for Recommendation Models
abs: https://t.co/1tD9oZFuAd

[Bilgin Ibryam @bibryam]

A #fantastic deep technical dive into all things Redis.
https://t.co/35cxZKMSFF

[AK @_akhaliq]

Enhancing Diffusion-Based Image Synthesis with Robust Classifier Guidance
abs: https://t.co/BrS5g1AkAu

[Mkodex1 @Manish_kumar3_1]

An amazing SQL cheat sheet!

Source:
@swapnakpanda
#SQL #CheatSheet #DataScience #MachineLearning #Analytics #AI #ML #Tech #IIoT #Python #TensorFlow #Java #ReactJS #Programming #Coding #womenintech #100DaysofCode #CodeNewbies #javascript #Java #SQL #linux

[Marcus Borba @marcusborba]

Researchers at Stanford and Meta AI have Developed a Dataset Pruning Technique for Scaling Artificial Intelligence #AI Training

https://t.co/pSYNPislvG @Marktechpost

#DeepLearning #BigData #Analytics #Robots #DataScience #MachineLearning #100DaysofCode #serverless #womenwhocode

[Daily AI Papers @papers_daily]

Discovering Agents

https://t.co/79U53iHSkl

Causal models of agents have been used to analyse the safety aspects of machine learning systems. This paper proposes the first formal causal definition of agents. From this...

🧵 👇

[Big Data Analytics News @BDAnalyticsnews]

Netflix ML Architecture

#ArtificialIntelligence #AI #ML #DataScience #DataScientists #CodeNewbies #Tech #deeplearning #CyberSecurity #Python #Coding #javascript #rstats #100DaysOfCode #programming #Linux #IoT #IIoT #BigData

[Andrew Ng @AndrewYNg]

Course 3 of the new Machine Learning Specialization is now available on @Coursera! We'd launched Courses 1&2 last month, and this final course teaches unsupervised learning, recommender systems, and reinforcement learning. Check it out here: https://t.co/qHZoEqmWm2

[Artem Moskalev @artemmoskalev]

Interested in contrastive representation learning? We use assignment theory to extend contrastive learning beyond contrasting pairs.

Contrasting quadratic assignments for set-based representation learning: https://t.co/kQ5CBSMfGu

w/ @isosnovik and @arnoldsmeulders

[Chelsea Finn @chelseabfinn]

Neural nets are brittle under domain shift & subpop shift.

We introduce a simple mixup-based method that selectively interpolates datapts to encourage domain-invariance

ICML 22 paper: https://t.co/cvV1itWux9

w/ @HuaxiuYaoML Yu Wang @zlj11112222 @liang_weixin @james_y_zou (1/3)

[Simone Scardapane @s_scardapane]

*Mitigating Neural Network Overconfidence with Logit Normalization*
#ICML paper by @OwenWei8 @SharonYixuanLi

Incredibly simple method to improve the calibration of a neural network: just enforce a constant norm on the logits.

Preprint is here: https://t.co/K0Tw7uIVYo

[Google AI @GoogleAI]

Learn how CMT-DeepLab uses a pixel clustering method for panoptic segmentation to notably improve performance, while kMaX-DeepLab simplifies the modification further advancing the state-of-the-art. Read more and grab the code for kMaX-DeepLab → https://t.co/n3D2XKg0ty

[elvis @omarsar0]

Machine Learning Operations (MLOps): Overview, Definition, and Architecture

Interesting overview of MLOPs. A great read for ML engineers.

https://t.co/29cDkUoUGm

[Sebastian Raschka @rasbt]

Nice! Another entry to check out for my Deep Learning for Tabular Datasets collection!