💡💡What is the best acc an MLP can get on CIFAR10❓
— Behnam Neyshabur (@bneyshabur) July 28, 2020
65%❓ No, 85%‼️
Trying to understand convolutions, we look at MDL and come up with a variant of LASSO that when applied to MLPs, it learns local connections and achieves amazing accuracy!
Paper: https://t.co/PUb2Q4tIBT
1/n pic.twitter.com/ijrX9CFJ41
🏅#TFCommunitySpotlight Winner: Javier Gamazo Tejero 🏅
— TensorFlow (@TensorFlow) July 22, 2020
Javier used TF to capture movement with a webcam and transfer it to Google Street View to give a virtual experience of walking through different cities. Great work, Javier!
Javier’s GitHub → https://t.co/jxtLx847vc pic.twitter.com/Ohq39BA2Sv
I came across an article about the large scale Face Recognition system at @odnoklassniki.
— Vladimir Iglovikov (@viglovikov) July 20, 2020
I liked how they created the train set. The trick about filtering false positives is also smart.
Translated it into English.https://t.co/ifOunH470b#DeepLearning #ArtificialInteligence
This👇🏾 make it all worth it.@kaggle GM @ChrisDeotte used @RAPIDSai tsne, knn, & kmeans + @TensorFlow CNN in a complex pipeline (no bugs nor workarounds💪🏾) to find similar images compare train and test distributions and more https://t.co/ZQPqMCC9Nt https://t.co/Zeo5RQfSgR 🔥🔥🔥
— Joshua Patterson (@datametrician) July 18, 2020
#ICML2020: We've developed a technique to mark the images in a data set so researchers can determine whether a particular #ML model has been trained using those images. Learn more about “radioactive data” here:https://t.co/u8eQH8R2jD Catch our talk at 3PM EST today.
— Facebook AI (@facebookai) July 15, 2020
Closed-Form Factorization of Latent Semantics in GANs
— AK (@ak92501) July 15, 2020
pdf: https://t.co/pYda24esEJ
abs: https://t.co/TTx4gwm5Xl pic.twitter.com/7YuVWnuquW
New tutorial!🚀
— Adrian Rosebrock (@PyImageSearch) July 13, 2020
Implementing basic R-CNN object detector from scratch with #Keras and #TensorFlow 2:
- Train on your own datasets
- Detailed tutorial
- Includes #Python codehttps://t.co/vlxyGoQuO7 đź‘Ť#DeepLearning #MachineLearning #ArtificialIntelligence #AI #DataScience pic.twitter.com/SFPER6aPqv
90% of the time your image classifier is not working as expected it's because of (1) image resizing issues (2) batch-norm :) https://t.co/DYX8EEl68Z
— Dumitru Erhan (@doomie) July 8, 2020
Today we present SpineNet, a novel alternative to standard scale-decreased backbone models for visual recognition tasks, which uses reordered network blocks with cross-scale connections to better preserve spatial information. Learn more below: https://t.co/Se9l6a5hEF
— Google AI (@GoogleAI) June 30, 2020
Excited to share our work @GoogleAI on Object-centric Learning with Slot Attention!
— Thomas Kipf (@thomaskipf) June 29, 2020
Slot Attention is a simple module for structure discovery and set prediction: it uses iterative attention to group perceptual inputs into a set of slots.
Paper: https://t.co/xfpjQwMuLP
[1/7] pic.twitter.com/0CzWO9B1fV
Interested in learning how to build OCR models? Here's a great code example from @A_K_Nain showing a model that can break Captchas. https://t.co/dmXDCNEppI pic.twitter.com/Rh3Py2CBqp
— François Chollet (@fchollet) June 26, 2020
Context R-CNN is a new object detection architecture that leverages temporal context from up to a month’s worth of images from a single camera to improve performance without a large corpus of training data. Learn more at https://t.co/j4zo61agGH pic.twitter.com/5boV1NB1OL
— Google AI (@GoogleAI) June 26, 2020
