@MSFTResearch AI for Science
London, England
Joined October 2016
- Tweets83
- Following226
- Followers132
- Likes232
Lukas Geiger retweeted
We made our ultra-fast and ultra-small inference engine for Arm Cortex-M processors even smaller. We now require 49% less RAM for 8-bit MobileNetV2 than TensorFlow Lite for Microcontrollers with Arm’s CMSIS-NN kernels.
Read the article here: blog.plumerai.com/2021/10/co…
Lukas Geiger retweeted
🏆 We built the world’s fastest and most memory-efficient deep learning inference software for Arm Cortex-M microcontrollers 🏆 for both Binarized Neural Networks and for 8-bit deep learning models.
blog.plumerai.com/2021/10/co…
Lukas Geiger retweeted
Our latest paper has been accepted to the #MLSys2021 conference! Congratulations Tom, Arash, Adam, Lukas, Tim, Leon, Jelmer and Koen!
We wrote a short blog post about the paper and the importance of Larq Compute Engine: blog.plumerai.com/2021/04/ml…
Lukas Geiger retweeted
It was great to see so many people attending our #tinyml webcast earlier this week! In case you missed the event, a recording of the talk is now online along with a short blog post explaining the main takeaways from our presentation: blog.plumerai.com/2021/01/ti…
Lukas Geiger retweeted
A fascinating talk on binarized neural networks for #tinyml by Lukas of @plumerai is now up at youtube.com/watch?v=f9SNqDej…, with slides at tinyml.org/wp-content/upload…
Lukas Geiger retweeted
This is starting in a few hours, come join our #tinyML webcast!
Don't miss tomorrow's #tinyML Talks 8AM Pacific us02web.zoom.us/webinar/regi… "Binarized Neural Networks on #microcontrollers" by Lukas Geiger, @plumerai
Lukas Geiger retweeted
Come join us on Tuesday for our @tinyMLTalks webcast! @_lgeiger will explain how we use 🚀Binarized Neural Networks🚀 to enable real-time deep learning on cheap, low-power edge devices. You can register here: us02web.zoom.us/webinar/regi…
Lukas Geiger retweeted
We've released v0.4 of Larq Compute Engine!
Some of our internal work optimizing BNN performance on microcontrollers has made its way to mobile and Raspberry Pi, as have a few major architectural improvements.
🚀 Full change log: github.com/larq/compute-engi…
Lukas Geiger retweeted
We just published blog post about open source tools for #DeepLearning presented at our social event at the @iclr_conf!
Shout-out to all the co-authors for their great contributions and efforts. Without your help, this would not have been possible!
neptune.ai/blog/iclr-2020-de…
(1/n)
Lukas Geiger retweeted
We’ve released Larq Compute Engine v0.3, featuring even faster BNN kernels and support for Python 3.8, TensorFlow 2.2, and Windows in the converter! 🎉
💻 Full release notes: github.com/larq/compute-engi…
📚 Docs: docs.larq.dev/compute-engine…
Lukas Geiger retweeted
The Larq Compute Engine team pushed out LCE v0.2.1 earlier today—same models, up to 15% lower latency. github.com/larq/compute-engi…
Lukas Geiger retweeted
We wrote a blog post about how we’re applying a software 2.0 approach in the new module for state-of-the-art binarized neural networks in Larq Zoo (`zoo.sota`). It also features some exciting improvements across the whole Larq stack: blog.larq.dev/2020/03/larq-e…
Lukas Geiger retweeted
We’ve just released Larq v0.9, featuring:
🔲 Non-zero padding
💾 Easier export for binary weights
📋 Improved model summaries
And lots more! 🎉 github.com/larq/larq/release…
Lukas Geiger retweeted
More about Larq Compute Engine:
📑 Docs: docs.larq.dev/compute-engine
👩💻 GitHub: github.com/larq/compute-engi…
💱 MLIR converter: docs.larq.dev/compute-engine…
📱 Android deployment: docs.larq.dev/compute-engine…
🥧 Raspberry Pi deployment: docs.larq.dev/compute-engine…
Really excited to finally share what we've been working on 🎉
We’re releasing a new open-source project today! 🎉
Larq Compute Engine is our solution for deploying Binarized Neural Networks to mobile and edge devices, with both an MLIR-based model converter and an inference engine integrated with @TensorFlow Lite: blog.larq.dev/2020/02/announ…
Lukas Geiger retweeted
Our binarized neural network training library, Larq, has been published in the Journal of Open Source Software! 🎉
📄 Read the paper by @_lgeiger et al. here: joss.theoj.org/papers/10.211…
🔎 Documentation: larq.dev
💻 Code: github.com/larq/larq
Just published in #JOSS_theOJ: 'Larq: An Open-Source Library for Training Binarized Neural Networks' doi.org/10.21105/joss.01746
Lukas Geiger retweeted
Just published in #JOSS_theOJ: 'Larq: An Open-Source Library for Training Binarized Neural Networks' doi.org/10.21105/joss.01746
Lukas Geiger retweeted
James, @_lgeiger and @khelwegen had a great time presenting our work on optimizing BNNs at #NeurIPS2019 last week!
See our paper, poster, and code here: plumerai.com/neurips19
Lukas Geiger retweeted
Want to know more? Come see us Wednesday 10:45am - 12:45pm in East Exhibition Hall B + C, at poster booth #103! neurips.cc/Conferences/2019/…
#NeurIPS #NeurIPS2019 #BNN
We’ll be @NeurIPSConf in Vancouver next week to present our paper:
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
📄 Paper: arxiv.org/abs/1906.02107
🖼 Poster: github.com/plumerai/rethinki…
💻 Code: github.com/plumerai/rethinki…
Lukas Geiger retweeted
We’ll be @NeurIPSConf in Vancouver next week to present our paper:
Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization
📄 Paper: arxiv.org/abs/1906.02107
🖼 Poster: github.com/plumerai/rethinki…
💻 Code: github.com/plumerai/rethinki…