​​TabNine showed deep learning code autocomplete tool based on GPT-2 architecture.

Video demonstrates the concept. Hopefully, it will allow us to write code with less bugs, not more.

Link: https://tabnine.com/blog/deep
Something relatively similar by Microsoft: https://visualstudio.microsoft.com/ru/services/intellicode

#GPT2 #TabNine #autocomplete #product #NLP #NLU #codegeneration

How to Segment Buildings on Drone Imagery with Fast.ai & Cloud-Native GeoData Tools
Blog by Dave Luo : https://medium.com/@anthropoco/how-to-segment-buildings-on-drone-imagery-with-fast-ai-cloud-native-geodata-tools-ae249612c321
#DeepLearning #Geospatial #Drones #MachineLearning #Tutorial

"Eidetic 3D LSTM: A Model for Video Prediction and Beyond"

Wang et al.: https://openreview.net/forum?id=B1lKS2AqtX

GitHub: https://github.com/metrofun/E3D-LSTM

#ArtificialIntelligence #DeepLearning #MachineLearning

Lookahead Optimizer: k steps forward, 1 step back by Geoffrey Hinton, Michael R. Zhang, James Lucas, Jimmy Ba paper : arxiv.org/abs/1907.08610

Trading via Image Classification
Cohen et al.: https://arxiv.org/abs/1907.10046v1
#ArtificialIntelligence #DeepLearning #Trading

Semi-parametric Object Synthesis. arxiv.org/abs/1907.10634

Efficient Detection and Quantification of Timing Leaks with Neural Networks. arxiv.org/abs/1907.10159

Tensorpack

A Neural Net Training Interface on TensorFlow, with focus on speed + flexibility

GitHub: https://github.com/tensorpack/tensorpack

#tensorflow #reinforcementlearning #neuralnetworks https://t.iss.one/ArtificialIntelligenceArticles

Pytorch-Transformers

A library of state-of-the-art pretrained models for Natural Language Processing (NLP)

By Hugging Face: https://huggingface.co/pytorch-transformers/

#naturallanguageprocessing #nlp #pytorch

GPU-Accelerated Atari Emulation for Reinforcement Learning"

Dalton et al.: https://arxiv.org/abs/1907.08467

#deeplearning #machinelearning #reinforcementlearning

3rd Workshop on Closing the Loop Between Vision and Language, October 28th, in conjunction with ICCV 2019 in Seoul, Korea

The scope of this workshop lies in the boundary of Computer Vision and Natural Language Processing. In recent years, there have been increasing interest in the intersection between Computer Vision and NLP. Researchers have studied a multitude of tasks, including generating textual descriptions from images and video, learning language embeddings of images and predicting visual classifiers from unstructured text. Recent work has extended the scope of this area to visual question answering, visual dialog, referring expression comprehension, vision-and-language navigation, embodied question answering and beyond.

In this workshop, we aim to provide a full day focused on these exciting research areas, helping to bolster the communication and share knowledge across tasks and approaches in this area, and provide a space to discuss the future and impact of Vision and Language technology. The workshop will also feature a new edition of the Large Scale Movie Description Challenge (details here), and the first VATEX challenge for Multilingual Video Captioning (details here).

Important dates:
------------------
Workshop paper submission deadline
Archival submissions: July 25, 2019
Non-archival submissions: September 15, 2019

Notification to authors
Archival submissions: August 15, 2019
Non-archival submissions: October 1, 2019

Camera ready deadline
Archival submissions (will be part of the proceedings): August 25, 2019
Non-archival submissions (will be posted online): October 15, 2019

Call for Papers:
----------------
We invite 4-page abstracts in ICCV format of new or previously published work addressing the topics outlined below. (For the previously published works re-formatting is not necessary.) We will make the accepted submissions available on our website as non-archival reports, and will also allow for novel submissions to appear in the ICCV workshop proceedings. The accepted works will be presented in the poster session and some will be selected for oral presentation. Topics of this workshop include but are not limited to (more details on our website):
Deep learning methods for vision and language
Established and novel problems in vision and language
Limitations of existing vision and language datasets and approaches

https://sites.google.com/site/iccv19clvllsmdc/important-dates

Workshop: October 28th, 2019
-----------------------------
Organizers:
Mohamed Elhoseiny, Assistant Professor, KAUST
Anna Rohrbach, Postdoctoral Scholar, UC Berkeley
Leonid Sigal, Associate Professor, University of British Columbia
Marcus Rohrbach, Research Scientist, Facebook AI Research
Xin Wang, PhD student, UC Santa Barbara

📌 Top 10 Deep Learning Github Repositories 2018

- In this article, we bring you a list of the Top 10 Deep Learning Github Repositories on a trend that has been sorted by the number of stars.

The Top 10 Deep Learning Repositories along with their respective links are:

1️⃣ Tensorflow

2️⃣ Keras

3️⃣ OpenCV

4️⃣ Caffe

5️⃣ Tensorflow-Examples

6️⃣ Machine-Learning-For-Software-Engineers

7️⃣ Deeplearningbook-Chinese

8️⃣ Deep-Learning-Papers-Reading-Roadmap

9️⃣ Pytorch

🔟 Awesome-Deep-Learning-Papers

References: https://www.techleer.com/articles/547-top-10-deep-learning-github-repositories-2018

Two positions in all areas of computer science

https://aprecruit.ucmerced.edu/JPF00834

Awesome Fraud Detection Research Papers.
https://github.com/benedekrozemberczki/awesome-fraud-detection-papers

SDNet: Semantically Guided Depth Estimation Network. arxiv.org/abs/1907.10659

Semi-parametric Object Synthesis. arxiv.org/abs/1907.10634

'The Deep Learning Revolution' - Geoffrey Hinton - RSE President's Lecture 2019


https://www.youtube.com/watch?v=re-SRA5UZQw&feature=youtu.be


https://t.iss.one/ArtificialIntelligenceArticles

best paper awards at #AC L2019

arxiv.org/abs/1906.01603