Top Tweets for #classicml
Most enterprise AI tasks don't need a language model. Prediction, anomaly detection, forecasting on structured data... that's #classicML, and it's faster, cheaper, and auditable.
#GenAI is a hammer. Not every problem is a nail.
@Alt_Data_Weekly @SymetryML
⚡#release omega-ml integrates Generative AI & Classic ML
#MLOps simplified - Deploy #GenerativeAI and #ClassicML on a single and independent platform. Significant for all companies in Swiss 🇨🇭 and EU 🇪🇺 that want to keep in full control of their data and algorithms.
Good engineering is not about memorizing syntax, but some interviews are. If you need a bit of a refresher, or want to show off at your next #DeepLearning happy hour, here are cheat sheets for Numpy, Pandas, Keras, and more by @Ahkailash1. #ClassicML https://t.co/u2okzgv78x
#DataScientists often think of complexity in terms of models. Simple models are good, but most of the work in delivering classifiers to users happens in infrastructure. This end-to-end music classifier is a great demonstration of this principle. #ClassicML https://t.co/Qfh2PB1bys
Collaborative Filtering, step 0 of recommendations systems, only uses co-occurence signals. We often want to use features about our content (tags, ...) and users (demographics, ...). @nickparsons shows how Factorization Machines combine both! #ClassicML https://t.co/HucLNUOp9t
In 2017, @UIzard published the pix2code paper. A few months later, @InsightDataAI Fellow @ShwinDa built on top of it, allowing the model to take sketches as input rather than images. Deep Learning advances are as frequent as Star Wars movies! #ClassicML https://t.co/L2mlmgCKsh
Ensembles are very powerful in #ML and routinely win @kaggle competitions. This paper is one of the first I saw mention the idea of using #DeepLearning checkpoints to form an ensemble. The idea has a lot of supporters including @jeremyphoward! #ClassicML https://t.co/WN3sBHaWSx
Sometimes, the ability of neural networks to map inputs and outputs of any type with little feature engineering can be very surprising. Here, the authors build a model that goes straight from speech in one language, to text in the other. #ClassicML https://t.co/F3k2AX5x4u
Neural Networks' ability to learn strong priors about the structure of images mean they can be used to compress images efficiently. This paper from MIT was one of the first ones I saw on the subject, and has a lot of good ideas in it. #ClassicML https://t.co/vNbBefNkEO
Speech synthesis has taken off recently, going from sounding like a sample out of a Daft Punk song to getting very close to human quality. @dhruvp gives one of the best explanations of a speech synthesis pipeline I've read. #ClassicML https://t.co/2UFv4kPwum
Features extracted by neural networks can be stored and used downstream across many use cases. In Computer Vision, these can be used for image similarity search. @Flickr outlines the challenges of deploying it in production. #ClassicML https://t.co/URfWsms13W
First, great post by @morgangiraud of @metaflow_ai on the foundational “Universal approximation theorem”, which justifies why we can expect good results by throwing massive neural networks at a problem. Find other classics I value by following #ClassicML! https://t.co/ZBFts0WuqH
Last Seen Hashtags on Sotwe
Most Popular Users
Elon Musk 
@elonmusk
241M followers
Barack Obama
@barackobama
119.2M followers
Cristiano Ronaldo
@cristiano
112M followers
Donald J. Trump
@realdonaldtrump
111.8M followers
Narendra Modi
@narendramodi
107.1M followers
Rihanna
@rihanna
98M followers
NASA
@nasa
92.2M followers
Justin Bieber
@justinbieber
91.2M followers
KATY PERRY
@katyperry
88.4M followers
Taylor Swift
@taylorswift13
82.3M followers
Lady Gaga
@ladygaga
73.8M followers
Virat Kohli
@imvkohli
71.1M followers
Kim Kardashian
@kimkardashian
70.2M followers
YouTube
@youtube
68.7M followers
Bill Gates
@billgates
64.3M followers
Neymar Jr
@neymarjr
64M followers
The Ellen Show
@theellenshow
62.4M followers
CNN
@cnn
61.8M followers
Selena Gomez
@selenagomez
61.5M followers
X
@x
60.8M followers