Profile cover photo
Profile photo
Grzegorz Wierzowiecki
184 followers
184 followers
About
Grzegorz's posts

Post is pinned.Post has attachment

Post has attachment
DIY fun of Barcode stickers prefix tree encoding! Happy printed batch of alphanum code128 barcodes, thanks to progress on my prefix tree of my barcodes encodings ! Used glabels-3 templates I publish here : https://github.com/barcode-utils/glabels-3-templates + gallery https://airtable.com/shrnM0shPlthoFrZo . For convenient growth of my prefix tree I used MindMup.com that allows to keep mind maps on Google Drive and develop in browser (and export to FreeMind which is my favourite non-cloud mind mapping tool). So happy that Dymo 450 LabelWriter works smoothly on all my Linuxes! (Arch Linux, Raspbian, Ubuntu Server)
PhotoPhotoPhotoPhotoPhoto
2/26/17
9 Photos - View album

Post has attachment
WDLabs PiDrive! 1TiB harddrive tailored for Raspberry Pi with case. Can't wait for next weekend to play with it! http://wdlabs.wd.com/category/wd-pidrive/
PhotoPhotoPhoto
2/26/17
3 Photos - View album

Post has shared content
Man points camera at ice – seconds later he captures the impossible on film as a piece of glacier the size of the Lower Manhattan falls into the ocean.

Post has shared content
I'm excited that the Google Brain team (g.co/brain) will have a decent presence at ICLR 2017 (http://www.iclr.cc), with 20 papers (including 4 papers chosen for oral presentation), plus an additional 4 papers in the workshop track. Of these, 9 of the papers have co-authors from our Brain Residency program (g.co/brainresidency), and another 8 have co-authors who were interns in our group. The Brain affiliated papers are below:

- Understanding deep learning requires rethinking generalization, by Chiyuan Zhang, Samy Bengio, Moritz Hardt, Benjamin Recht, Oriol Vinyals, http://openreview.net/forum?id=Sy8gdB9xx (Intern co-author), Oral
- Neural Architecture Search with Reinforcement Learning, by Barret Zoph and Quoc Le, http://openreview.net/forum?id=r1Ue8Hcxg (Brain Resident co-author), Oral
- Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data, by Nicolas Papernot, Martín Abadi, Úlfar Erlingsson, Ian Goodfellow, Kunal Talwar, http://openreview.net/forum?id=HkwoSDPgg, Oral
- Q-Prop: Sample-Efficient Policy Gradient with An Off-Policy Critic, by Shixiang (Shane) Gu, Timothy Lillicrap, Zoubin Ghahramani, Richard E. Turner, Sergey Levine, http://openreview.net/forum?id=SJ3rcZcxl (Intern co-author), Oral
- Adversarial Machine Learning at Scale, by Alexey Kurakin, Ian J. Goodfellow, Samy Bengio, http://openreview.net/forum?id=BJm4T4Kgx
- Density estimation using Real NVP, by Laurent Dinh, Jascha Sohl-Dickstein, Samy Bengio, http://openreview.net/forum?id=HkpbnH9lx (Intern co-author)
- Learning to Remember Rare Events, by Lukasz Kaiser, Ofir Nachum, Aurko Roy, Samy Bengio, http://openreview.net/forum?id=S1yTEt9ex (Brain Resident co-author)
- Categorical Reparameterization with Gumbel-Softmax, by Eric Jang, Shixiang (Shane) Gu, Ben Poole, http://openreview.net/forum?id=rkE3y85ee (Intern co-author)
- HyperNetworks, by David Ha, Andrew Dai, Quoc V. Le, http://openreview.net/forum?id=rkpACe1lx (Brain Resident co-author)
- Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer, by Noam Shazeer, Azalia Mirhoseini, Krzysztof Maziarz, Andy Davis, Quoc Le, Geoffrey Hinton, Jeff Dean, http://openreview.net/forum?id=B1ckMDqlg (Brain Resident co-author)
- Learning a Natural Language Interface with Neural Programmer, by Arvind Neelakantan, Quoc V. Le, Martín Abadi, Andrew McCallum, Dario Amodei, http://openreview.net/forum?id=ry2YOrcge (Intern co-author)
- Deep Information Propagation, by Samuel Schoenholz, Justin Gilmer, Surya Ganguli, Jascha Sohl-Dickstein, http://openreview.net/forum?id=H1W1UN9gg (Brain Resident co-author)
- Decomposing Motion and Content for Natural Video Sequence Prediction, by Ruben Villegas, Jimei Yang, Seunghoon Hong, Xunyu Lin, Honglak Lee, http://openreview.net/forum?id=rkEFLFqee
- Capacity and Trainability in Recurrent Neural Networks, by Jasmine Collins, Jascha Sohl-Dickstein, David Sussillo, http://openreview.net/pdf?id=BydARw9ex (Brain Resident co-author)
- Unrolled Generative Adversarial Networks, by Luke Metz, Ben Poole, David Pfau, Jascha Sohl-Dickstein, http://104.155.136.4:3000/forum?id=BydrOIcle (Brain Resident co-author)
- A Learned Representation For Artistic Style, by Vincent Dumoulin, Jonathon Shlens, Manjunath Kudlur, http://openreview.net/forum?id=BJO-BuT1g (Intern co-author)
- Identity Matters in Deep Learning, by Moritz Hardt, Tengyu Ma, http://openreview.net/forum?id=ryxB0Rtxx
- Latent Sequence Decompositions, by William Chan, Yu Zhang, Quoc Le, Navdeep Jaitly, http://104.155.136.4:3000/forum?id=SyQq185lg (Intern co-author)
- Improving policy gradient by exploring under-appreciated rewards, by Ofir Nachum, Mohammad Norouzi, Dale Schuurmans, http://openreview.net/forum?id=ryT4pvqll (Brain Resident co-author)
- Adversarial Training Methods for Semi-Supervised Text Classification, by Takeru Miyato, Andrew M. Dai, Ian Goodfellow, https://openreview.net/forum?id=r1X3g2_xl
- Adversarial examples in the physical world, by Alexey Kurakin, Ian J. Goodfellow, Samy Bengio, http://openreview.net/forum?id=S1OufnIlx, Workshop
- Short and Deep: Sketching and Neural Networks, by Amit Daniely, Nevena Lazic, Yoram Singer, Kunal Talwar, http://openreview.net/forum?id=r1br_2Kge, Workshop
- Unsupervised Perceptual Rewards for Imitation Learning, by Pierre Sermanet, Kelvin Xu, Sergey Levine, http://openreview.net/pdf?id=Bkul3t9ee (Brain Resident co-author), Workshop
- Tuning Recurrent Neural Neworks with Reinforcement Learning, by Natasha Jaques, Shixiang (Shane) Gu, Richard E. Turner, Douglas Eck, http://openreview.net/forum?id=BJ8fyHceg, (Intern co-author), Workshop

You can find the full list of accepted papers at ICLR 2017 here:
https://openreview.net/group?id=ICLR.cc/2017/conference

Edit: Added intern identification to one of the papers


Post has shared content

Post has shared content
Nice to see the release of Cloud Spanner today! I helped design and implement Spanner along with many other people in order to provide a strongly consistent, geographically distributed database system that could be used in our products. Google's advertising systems was one of our primary early customers for Spanner. Now the same system can be used externally.

Engineers at Quizlet did a nice comparison of Cloud Spanner's performance and scaling characteristics compared with MySQL:

https://quizlet.com/blog/quizlet-cloud-spanner

A detailed paper about Spanner appeared in OSDI 2012:

https://research.google.com/archive/spanner.html

To all the people continuing to improve Spanner today, congrats on the launch! Great work!

Post has shared content

Post has shared content
+Esteban Real, +Jon Shlens, Xin Pan, and +Vincent Vanhoucke in the Google Brain team and Stefano Mazzocchi in another team at Google Research just released a new public dataset called YouTube-BoundingBoxes, consisting of 5 million human annotated bounding boxes across 380,000 video segments.

Deep learning models for handling video rather than just static images are likely to be the next frontier for computer vision research, and this large dataset is likely to be an important new tool in assessing the effectiveness of a wide variety of video models in the areas of localization, detection, and object tracking.

There's a more detailed associated Arxiv paper that describe the dataset and the methodology used for collecting it in more detail: https://arxiv.org/pdf/1702.00824v1.pdf

Nice work, everyone!

Post has shared content
Wait while more posts are being loaded