"Machine Learning Systems are Stuck in a Rut"
By Paul Barham and Michael Isard: https://dl.acm.org/citation.cfm?id=3321441
#TensorFlow #PyTorch #Swift #MachineLearning

Provably Robust Boosted Decision Stumps and Trees against Adversarial Attacks
Maksym Andriushchenko and Matthias Hein: https://arxiv.org/abs/1906.03526
Code: https://github.com/max-andr/provably-robust-boosting
#MachineLearning #Cryptography #Security

Deep Neuroevolution of Recurrent and Discrete World Models

https://arxiv.org/abs/1906.08857

Post-Doctoral Fellowship on Automatic Machine Learning (AutoML)

We are seeking a highly creative and motivated post-doctoral fellow to join the Data Mining Group at the Eindhoven University of Technology. The candidate will be working in collaboration with Dr. ir. Joaquin Vanschoren, as well as the OpenML core team and Amazon Research.

The field of automated machine learning (AutoML) aims to automatically build machine learning models in a data-driven, objective, and automatic way. We are building an AutoML playground (an 'AutoML Gym') to train AutoML systems on many different problems and get increasingly better over time. Similar to the OpenAI Gym, which trains reinforcement learning agents on many different scenario's, the AutoML Gym will train and test many different AutoML systems (agents) on many challenging problems. We will continuously track the performance of the AutoML agents, and store this information in a meta-data repository, a shared memory that can be accessed by any AutoML agent to perform meta-learning and become increasingly better over time.

This work is funded by an Amazon Research Award. It will be set in a very interactive environment, including the Eindhoven Data Mining Group, the OpenML team, the AutoML community, and Amazon research.

To apply, please submit requested documents at https://jobs.tue.nl/en/vacancy/postdoctoral-fellow-on-automatic-machine-learning-661204.html. For further questions, please contact dr. Joaquin Vanschoren by e-mail ([email protected]).

We will start processing applications as of July 15th 2019, and until the position is filled. The fellow can start as soon as possible.

Thanks for disseminating this opportunity,
Joaquin Vanschoren

Overview of deep learning in medical imaging


https://link.springer.com/article/10.1007%2Fs12194-017-0406-5

How do neural networks see depth in single images?

Paper link: arxiv.org/abs/1905.07005

6 thoughts on “The “η-trick” or the effectiveness of reweighted least-squares”
https://francisbach.com/the-%ce%b7-trick-or-the-effectiveness-of-reweighted-least-squares/

Neural Decipherment via Minimum-Cost Flow: from Ugaritic to Linear B
Luo et al.: https://arxiv.org/abs/1906.06718
#ArtificialIntelligence #Computation #Language

Sensor-Actuator Networks
Michiel van de Panne and Eugene Fiume: https://www.cs.ubc.ca/~van/papers/1993-siggraph-sans.pdf
#ArtificialIntelligence #MachineLearning #Robotics

25 Open Datasets for Deep Learning Every Data Scientist Must Work With


https://www.analyticsvidhya.com/blog/2018/03/comprehensive-collection-deep-learning-datasets/

Label Set Operations (LaSO) Networks for Multi-Label Few-Shot Learning
https://www.ibm.com/blogs/research/2019/06/few-shot-learning/

Machine Learning Math Notations.
By Shan Hung-Wu

Download Link: https://nthu-datalab.github.io/ml/slides/Notation.pdf

Stanford Machine Learning Class Notes (CS229)
BY TANUJIT CHAKRABORTY
Download Link: https://www.ctanujit.org/uploads/2/5/3/9/25393293/machine_learning_notes__cs229_.pdf

Approximating Wasserstein distances with PyTorch
https://dfdazac.github.io/sinkhorn.html

Explain Yourself! Leveraging Language Models for Commonsense Reasoning
Rajani et al.: https://arxiv.org/abs/1906.02361
Github: https://github.com/salesforce/cos-e
Blog: https://blog.einstein.ai/leveraging-language-models-for-commonsense/
#Computation #Language #MachineLearning

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog
Jaques et al.: https://arxiv.org/abs/1907.00456
Code https://github.com/natashamjaques/neural_chat/tree/master/rl
#ArtificialIntelligence #DeepLearning #ReinforcementLearning

PhD fellow in Theoretical Machine Learning
University of Copenhagen, Denmark

More Details: https://www.marktechpost.com/job/phd-fellow-in-theoretical-machine-learning/
Department of Computer Science, Faculty of Science at University of Copenhagen is offering a PhD scholarship in Theoretical Machine Learning commencing 01.10.2019 or as soon as possible thereafter.

Dr. Elizabeth Chrastil, PI of the Spatial Neuroscience Laboratory in the Department of Neurobiology & Behavior at the University of California, Irvine, is seeking a Junior or Assistant Specialist/Research Assistant. This person will enable research as part of a team and, depending on experience level, may also conduct some independent research projects. The Spatial Neuroscience Lab uses dynamic and interdisciplinary research methods to answer questions about how the brain processes information to keep us oriented as we navigate through a complicated world. Our primary techniques are fully immersive virtual reality and neuroscience brain imaging using functional magnetic resonance imaging (fMRI) and electroencephalography (EEG). The position is ideal for recent graduates interested in pursuing graduate work in cognitive neuroscience, medicine, psychology, or bioengineering as a way to gain experience and make scientific and scholarly contributions to neuroscience.

Duties: Primary research responsibilities include recruiting participants for experiments, preparing stimulus presentation scripts, data collection for neuroimaging and immersive virtual reality experiments, computer programming and configuring testing computers for behavioral testing, writing and editing code to process, analyze and visualize experimental data, and assisting the research team in processing and analyzing data from these experiments. Lab Manager responsibilities include training and supervising undergraduate research assistants, tracking study progress, and some administrative duties (e.g. IRB protocol management and overseeing lab operations).

BASIC QUALIFICATIONS:
· Bachelor’s degree in neuroscience, psychology, cognitive science, biomedical sciences, or a related field and previous research experience.
· The ability to work independently, efficiently, and comfortably in a multidisciplinary team environment; exceptional organizational and problem solving skills; attention to detail; excellent written and verbal communication; a strong work ethic.
PREFERRED QUALIFICATIONS:
· Experience with any of the following is highly desirable: programming (particularly Matlab and python), neuroimaging analysis software (e.g. SPM, FSL, Freesurfer), statistical analysis software (e.g. R, SPSS), experimental software (e.g. EPrime, Unity).

Initial appointment is for one year (beginning approximately September 1, 2019) at 100% time, with a comprehensive benefits package. Continuation beyond one year will be based on performance and availability of funding. The salary is based on UCI’s salary scales and dependent upon qualifications.
Applicants should submit: 1) cover letter describing your qualifications, research interests and career goals, 2) a current curriculum vitae, 3) contact information (including names, email addresses, and telephone numbers) for 3 references who can provide letters upon request.
Submit applications electronically at https://recruit.ap.uci.edu/JPF05440

For questions about the position, contact Dr. Elizabeth Chrastil at [email protected]. For information on the Spatial Neuroscience Laboratory, go to https://chrastil.geog.ucsb.edu

I'm looking for a PhD student for my new lab at the Department of Psychology at the University of York (UK).
The position is fully funded and will start in October 2019.

The student will work on vision in naturalistic contexts, such as how we efficiently perceive multiple objects and complex natural scenes. A particular emphasis will be put on how the structure of natural scenes (i.e., the typical distribution of information across scenes) facilitates efficient visual processing, both on the behavioral and the neural level.
The PhD project will approach these topics using a variety of methods, including psychophysics, M/EEG, and functional MRI.
For further information on my previous research on these topics, please check out my webpage: https://www.danielkaiser.net

The University of York offers a great environment for conducting this PhD project, with both great vision science and neuroimaging communities. The Department of Psychology regularly scores among the best psychology institutes worldwide, and is among the top-10 institutes in the UK.

The full advertisement can be found here, and includes further information about the position and requirements to apply: https://tinyurl.com/y2t8l7br

Before making an application, candidates are encouraged to informally contact me via email at: [email protected]