[Google Brain Object detection] EfficientDet: Scalable and Efficient Object Detection implementation by Signatrix GmbH



Source code: https://github.com/signatrix/efficientdet

The Neuro-Symbolic Concept Learner: Interpreting Scenes, Words, and Sentences From Natural Supervision
Mao et al.: https://arxiv.org/abs/1904.12584
#ArtificialIntelligence #NeuroSymbolic #AIDebate

Geometric Capsule Autoencoders for 3D Point Clouds
Nitish Srivastava, Hanlin Goh, Ruslan Salakhutdinov : https://arxiv.org/pdf/1912.03310.pdf
#ArtificialIntelligence #DeepLearning #MachineLearning

Analyzing and Improving the Image Quality of StyleGAN
Karras et al.:https://arxiv.org/abs/1912.04958
Github: https://github.com/NVlabs/stylegan2
#ArtificialIntelligence #DeepLearning #GenerativeAdversarialNetworks

10 ML & NLP Research Highlights of 2019
https://ruder.io/research-highlights-2019/

Practical AI
A practical approach to machine learning to enable everyone to learn, explore and build : https://github.com/practicalAI/practicalAI
#Python #Numpy #Pandas

A nice collection of resources to learn more about ML and AI (talks, posts, papers, summaries)

https://github.com/brylevkirill/notes

Father of GANs Ian Goodfellow Splits Google For Apple
https://medium.com/syncedreview/father-of-gans-ian-goodfellow-splits-google-for-apple-279fcc54b328

One of the most interesting write ups I've ever seen.
https://anatomyof.ai/

Maybe good to know? Difference between STED, SIM and STORM:
https://www.technologynetworks.com/neuroscience/articles/what-is-super-resolution-microscopy-sted-sim-and-storm-explained-328572

Yoshua Bengio brainstorm with students. Very interesting discussion

https://www.youtube.com/watch?v=g9V-MHxSCcs

10 PhD and postdoc positions in ML for Earth sciences
We have several open positions (PhD and postdocs) in the Image and Signal Processing (ISP) group in the Universitat de Valencia, Spain, https://isp.uv.es.
Information about the different projects in https://isp.uv.es/openings
Master/PhD in maths, physics, ecology, computer/data science, remote sensing, environmental or climate science
Experience in machine learning, deep learning, image processing, time series analysis, statistics, Bayesian inference, interest in ecology, remote sensing, Earth observation and climate science
Apply here accordingly
Deadline: January 15th 2020

Postdoc position at Stanford
Professor Stefano Ermon is seeking an outstanding researcher for a postdoctoral position at Stanford (https://cs.stanford.edu/~ermon/website/). The postdoc will carry out Machine Learning research on a broad range of topics, including learning with limited supervision, generative models, and imitation learning. We welcome applications from candidates with diverse educational backgrounds.


Required qualifications:
A Ph.D. (completed by start of employment) in Computer Science, or a relevant area

Publication record in top Machine Learning conferences

Experience with deep learning frameworks (e.g., TensorFlow, PyTorch)


Duration: This is a one-year position with the expectation of renewal for additional years conditional on performance.

To apply: Applicants should send their C.V. and research statement to [email protected]. Review of applications will begin immediately after and will continue until the position is filled.

Stanford University is an Equal Opportunity, Affirmative Action Educational Institution and Employer, Title IX University. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, disability status, protected veteran status, or any other characteristic protected by the law. Stanford University is an E-Verify Employer.

Improving Deep Neuroevolution via Deep Innovation Protection
Sebastian Risi and Kenneth O. Stanley : https://arxiv.org/abs/2001.01683
#ArtificialIntelligence #DeepLearning #Neuroevolution

New Deep Learning Baseline for Image Classification called FrequentNet just got released!
Paper: https://arxiv.org/pdf/2001.01034.pdf
The authors generalize the idea from the method called ”PCANet” (Chan et al., 2015) to achieve a new baseline deep learning model for image classification. Instead of using principal component vectors as the filter vector in ”PCANet”.

AEI: Artificial ‘Emotional’ Intelligence

https://towardsdatascience.com/aei-artificial-emotional-intelligence-ea3667d8ece

Best NLP Research of 2019

@ArtificialIntelligenceArticles https://opendatascience.com/best-nlp-research-of-2019/
@ArtificialIntelligenceArticles

Artificial Intelligence for Social Good: A Survey
Zheyuan Ryan Shi, Claire Wang, Fei Fang : https://arxiv.org/abs/2001.01818
#AI4SG #ArtificialIntelligence #AIGovernance

Data project checklist
By Jeremy Howard : https://www.fast.ai/2020/01/07/data-questionnaire/
#ArtificialIntelligence #DataScience #MachineLearning