Tweetovi
- Tweetovi, trenutna stranica.
- Tweetovi i odgovori
Blokirali ste korisnika/cu @vespaengine
Jeste li sigurni da želite vidjeti te tweetove? Time nećete deblokirati korisnika/cu @vespaengine
-
Vespa improvements from January https://blog.vespa.ai/vespa-product-updates-january-2020/ … Among other things this includes new tensor functions needed to run BERT models. All of it already released and running in production of course.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The big data maturity levels https://medium.com/@bratseth/the-big-data-maturity-levels-8b61875032cc?source=friends_link&sk=351dc04418bf220d1b76c6a25ff05721 … Tag your org!
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
One of many applications which uses
@vespaengine in@verizonmedia. Check out this presentation from AWS re:Invent 2019: How Verizon Media implemented push notification using Amazon DynamoDB. 150K/s push notifications, resolving of targets done by Vespa. https://www.youtube.com/watch?v=FwWT6a3ikZ4 …pic.twitter.com/xpfxlgnJks
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Getting started with machine-learned ranking using Vespahttps://medium.com/vespa/learning-to-rank-with-vespa-9928bbda98bf …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
If you have http://Vespa.ai it's not too late to make yourself a state of the art and infinitely scalable e-commerce site in time for Black Friday.
@jobergum explains how inhttps://medium.com/vespa/e-commerce-search-and-recommendation-with-vespa-ai-a49c98f97e68 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Working on new sample applications for
@vespaengine this morning. A simple neural network trained with@PyTorch, exported in@onnxai format and deployed to Vespa for serving. Text embeddings from Google's Universal Sentence Encoder. Work building on https://github.com/vespa-engine/sample-apps/tree/master/semantic-qa-retrieval …pic.twitter.com/NVxdrQlIhX
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
New http://Vespa.ai /
@vespaengine sample app which reproduces Google's paper on semantic retrieval for Q-A applications ( https://arxiv.org/abs/1907.04780 ) released today https://github.com/vespa-engine/sample-apps/tree/master/semantic-qa-retrieval …. 44% of 88K questions with the correct answer @ position 1 on SQuAD v1.1 train setHvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
For more on how to use reinforcement learning for recommendation see https://medium.com/vespa/serving-article-comments-using-reinforcement-learning-of-a-neural-net-83f7ded17e8f …https://twitter.com/adichad/status/1188827708014370816 …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Comparing nearest neighbor ranking performance of http://Elastic.co versus http://Vespa.ai using dense tensor dot product: Vespa 5x faster than Elastic on same hw, same data and queries. Try it out!https://github.com/jobergum/dense-vector-ranking-performance …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Newly released Vespa features: https://blog.vespa.ai/post/188063440936/vespa-product-updates-september-2019-tensor … We added support for float tensors values, in addition to double. Obviously useful if you are memory bound, but we also measure up to 30% better ranking performance due to reduced memory bandwidth usage.
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It's been a good summer for coding in the north

We got some new features in Vespa released: BM25 ranking feature, searchable parents, tensor summary features and metric exporthttps://blog.vespa.ai/post/187148684196/vespa-product-updates-august-2019-bm25-rank …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Do you wish
@jonbratseth could be in your living room right now talking about Scalable Machine-Learned Model Serving? Not a problem! Follow this link to make your wish a reality: https://www.youtube.com/watch?v=tTIATQk-V00&list=PLq-odUc2x7i9-bGb8F8ytYBfCAzcmpaUe&index=21 …pic.twitter.com/4AAY88s5V1
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Applying machine learning in online applications requires solving the problem of model serving. At
#bbuzz@jonbratseth explains the problem and architectural solution, and shows how Vespa can be used to implement the solution. Read the full abstract here: https://berlinbuzzwords.de/19/session/scalable-machine-learned-model-serving …pic.twitter.com/gJQQSdUYuy
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
We're starting a new series of posts where we provide a complete and scalable Vespa application with a frontend for a popular use case. First out: Shopping sites!https://blog.vespa.ai/post/184617258876/vespa-use-case-shopping …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
Join us at https://BigDataAIConference.com in Dallas, TX, June 27.-29. where
@jonbratseth will talk about using Vespa to evaluate ML models over many data points with low latency.Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Applying machine learning in online applications requires solving the problem of model serving. At
#bbuzz@jonbratseth explains the problem and architectural solution, and shows how Vespa can be used to implement the solution. Read the full abstract here: https://berlinbuzzwords.de/19/session/scalable-machine-learned-model-serving …pic.twitter.com/WuEQ6ufWUH
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
With
@vespaengine you can fine tune your term frequency contribution by custom occurrence tables & also built in rank-type for different type of text fields https://docs.vespa.ai/documentation/reference/nativerank.html#boost-tables … & https://docs.vespa.ai/documentation/reference/rank-types.html …. In addition the nativeRank of Vespa also includes proximity ranking.https://twitter.com/IntranetFocus/status/1114135425583603712 …Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
The Vespa Engine proslijedio/la je Tweet
Are you familiar with
@vespaengine? It is an#opensource service engine for processing data and making inferences at scale in#realtime . Learn with@jonbratseth at#JOTB19#BigData https://buff.ly/2TNZfhl pic.twitter.com/SmqeSZkEHG
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
New Vespa features released over the last month:http://blog.vespa.ai/post/183115205176/vespa-product-updates-february-2019-boolean …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi -
It turns out that when you open source 1.7M lines of code in 150 flat modules people will keep asking for directions. Today we're publishing a map to the http://Vespa.ai code base.https://github.com/vespa-engine/vespa/blob/master/Code-map.md …
Hvala. Twitter će to iskoristiti za poboljšanje vaše vremenske crte. PoništiPoništi
Čini se da učitavanje traje već neko vrijeme.
Twitter je možda preopterećen ili ima kratkotrajnih poteškoća u radu. Pokušajte ponovno ili potražite dodatne informacije u odjeljku Status Twittera.