Meta-Learning Deep Energy-Based Memory Models
Bartunov et al.: https://arxiv.org/abs/1910.02720
#MachineLearning #MetaLearning #EnergyBasedMemoryModels

Announcing NeurIPS Meetups!
By Neural Information Processing Systems Conference : https://medium.com/@NeurIPSConf/announcing-neurips-meetups-44b2385c67a2
#NeurIPS #Meetup #NeurIPS2019

GPyTorch
Gaussian processes for modern machine learning systems.
GitHub: https://github.com/cornellius-gp/gpytorch
Website: https://gpytorch.ai
#PyTorch #NeuralNetworks #MachineLearning

@ArtificialIntelligenceArticles

Deep learning method transforms shapes


https://www.sciencedaily.com/releases/2019/10/191018125516.htm

Information Closure Theory of Consciousness
https://arxiv.org/pdf/1909.13045.pdf

@ArtificialIntelligenceArticles

PhD positions in Deep Learning for Satellite Image Analysis at TU Berlin
The Remote Sensing Image Analysis (RSiM) group at the Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin, Germany is looking for highly motivated PhD candidates. The research of the PhD candidates will aim at developing innovative machine learning techniques (with a special focus on deep learning) for the analysis of big data from space.

The main topics include:
developing deep neural network models that can overcome the data imbalance problems for satellite image classification; and
developing active learning methods that are applicable to the designed deep neural networks.
The successful candidates will begin on January 2020 and will have a duration of 3 years. MSc degree is required in computer engineering or computer science with experience in computer vision, deep learning for image understanding. Very good command of German and English is required.

Interested candidates are requested to email their CVs to Prof. Begum Demir ([email protected]).

Multiple ML and AI Postdoc Opportunities at Northwestern University Feinberg School of Medicine
We are recruiting multiple postdoctoral fellows in the Division of Health and Biomedical Informatics at Northwestern University’s Feinberg School of Medicine. The postdoctoral fellow is expected to conduct research under guidance from Dr. Yuan Luo, Associate Professor and Chief AI Scientist, Northwestern University Clinical and Translational Sciences Institute. Our group website: https://labs.feinberg.northwestern.edu/lyg/. The fellow will also have the opportunities to work closely with top-notch clinicians from Northwestern Memorial Hospital, and strong supporting staff from Northwestern Medicine Enterprise Data Warehouse Team.

The successful candidate will have PhD in EECS, Biomedical Informatics, IEMS, Physics or related fields with solid programming skills. Experiences in some of the following areas are desirable: Machine Learning (ML) and/or Natural Language Processing (NLP) and/or time series analysis and/or -omic analysis. The candidate should demonstrate good communication skills and ability to work in a collaborative environment, to coordinate and supervise part of the research project.

We offer a competitive salary and an initial appointment of 12 months, starting 2019/2020. Extension of the postdoctoral position for up to 3 years is possible. Northwestern University is an exceptional research institution that has a world-class medical school and is an emerging hub in biomedical informatics; our department is located in downtown Chicago, one of the most vibrant cities in the US. Be part of a prestigious institution that offers great benefits, and enjoy our lakefront working environment.

Please send your application to Yuan Luo <[email protected]>, which should include:
- Curriculum vitae
- List of publications (attach a copy of one of your strongest papers)
- Contact details for 2 to 3 references

Northwestern University is an Equal Opportunity/Affirmative Action Employer.

Postdoctoral position on Machine Learning at FCUP / University of Porto in collaboration with Bosch
Postdoctoral position on Machine Learning at FCUP / University of Porto in collaboration with Bosch
--------------------------------------------------------------------------------------------

**Deadline: 28/10/2019

The Department of Computer Science / U. Porto is looking for a highly motivated post doc to join the team of researchers working on the SafeCities project, a joint venture between U. Porto and the company Bosch. The topic is Machine Learning for Sensor Data for false alarm reduction. The aims of the project are to develop Machine Learning models and algorithms, statistical data analysis and variable selection, in the context of large scale and heterogeneous data. The selected candidate main tasks will be to develop research in these areas and give support to the management of the team of junior researchers.

The selected candidate will join the Machine Learning team of FCUP / INESC TEC and will have the opportunity to work in an exciting and young environment in close interaction with research engineers, PhD students and post-doctoral researchers who are working on varied aspects that concern Machine Learning, Information Extraction and Computer Science. The candidate will also have close interaction with our project partners at Bosch in an industry setting.

The ideal candidate will have a PhD in Machine Learning or equivalent and the following skills:

* Strong motivation to work with ML algorithms, demos and tools;
* Theoretical background and hands-on experience on Machine Learning / Data Mining / Data Science;
* Experience with ML toolkits and packages such as TensorFlow;
* Good communication skills and ability to cooperate within a team;
* Good knowledge of programming languages such as, Python, R and Java;
* Knowledge of development and versioning tools (e.g. GIT);
* Experience with HPC / GPU and cloud computing;
* Motivation to co-coordinate work-packages, co-supervise students and help with project management;
* Motivation to articulate with other projects on the topic and go after funding for the research line.

This position is supported by the Project “Safe Cities”, ref. POCI-01-0247-FEDER-041435, financed by Fundo Europeu de Desenvolvimento Regional (FEDER), through COMPETE 2020 and Portugal 2020.

The successful candidate will be offered a grant with the net monthly value of 1509,80€ which can be extended until the end of the project (3 yrs). There is a possibility of continuing research after the end of the project subject to the candidate performance and funding availability.

PhD and MSc positions for this project are also available.

To submit send en email to ([email protected]; [email protected]; [email protected]) with the subject "91 Bolseiro Doutorado (FCUP) n.º 1 Sub-Projeto 2”.

Please attach the following documents in pdf format:
- Motivation letter
- Academic certificates
- Detailed curriculum vitae
- Other relevant documents such as reference letters

**Deadline: 28/10/2019

More info (in Portuguese): https://sigarra.up.pt/up/pt/noticias_geral.ver_noticia?p_nr=6016

PhD scholarships in Statistics & Computer Science @Bocconi, Milano
PhD in Statistics & Computer Science - a.y. 2020-2021
Call for applications for PhD student positions
***********************

The Bocconi PhD School provides 7 scholarships for the PhD in Statistics and Computer Science, and a position with tuition waiver.

* Scholarship amount *
20.280 euro per annum in the 1st and 2nd year
15.343 euro per annum in the 3rd and 4th year

Further funding is available through teaching and research assistantship.
Visit www.unibocconi.eu/admissionphd for detailed information.

Applications are due by February 3, 2020

Within the PhD School at Bocconi University, the four-year PhD program in Statistics and Computer Science is a high profile and rigorous doctoral program that develops strong mathematical, statistical, computational and programming backgrounds.

The curriculum is structured into two tracks: Statistics and Computer Science. The first year includes courses that are compulsory for all enrolled PhD students. The second-year features track-specific and elective courses that provide students with a more specialized competence and focus on topics that may be the object of the doctoral dissertation.

Dedicated mentorship is offered to students throughout their time at Bocconi. Multidisciplinary interchange with other graduate programs in Bocconi’s PhD School, as well as research experience abroad, are also encouraged.

The Faculty includes internationally acknowledged top researchers in Statistics, Computer Science, Decision Theory, Statistical Physics and Machine Learning. The program also benefits from contributions of authoritative visiting professors who deliver short monographic courses.

Highly qualified and motivated students with M.Sc. degrees in in Statistics, Mathematics, Computer Science, Economics, Physics, Engineering and related areas, as well as other quantitatively-oriented fields, are encouraged to apply for admission.

Applicants should hold or be on their way to hold a graduate degree or equivalent.

For further information about the PhD program in Statistics and Computer Science at Bocconi, visit www.unibocconi.eu/phdstatscompscience and feel free to contact:
Antonio Lijoi ([email protected])
Angela Baldassarre, PhD administrative assistant
([email protected])

Antonio Lijoi
Director, PhD program in Statistics and Computer Science
Bocconi University

Does the brain do backpropagation? CAN Public Lecture - Geoffrey Hinton

One of the best recent talks of Prof. Geoffrey Hinton
online on computation in the brain. Intriguingly, the proposed relation between the neuron firing rate and the error signal looks quite similar to the Euler-Lagrange equation of motion in Physics.

https://www.youtube.com/watch?v=qIEfJ6OBGj8

@ArtificialIntelligenceArticles

Using Speech Synthesis to Train End-to-End Spoken Language Understanding Models
Loren Lugosch, Brett Meyer, Derek Nowrouzezahrai, Mirco Ravanelli : https://arxiv.org/abs/1910.09463
#SpokenLanguageUnderstanding #SpeechProcessing #MachineLearning

"MultiFiT: Efficient Multi-lingual Language Model Fine-tuning"
Eisenschlos et al.: https://arxiv.org/abs/1909.04761
Post: https://nlp.fast.ai/classification/2019/09/10/multifit.html
#ArtificialIntelligence #MachineLearning #NaturalLanguageProcessing

Quantum supremacy using a programmable superconducting processor




https://www.nature.com/articles/s41586-019-1666-5?fbclid=IwAR382bUHaSOgZpZDw7HMSAESLXQ_skyNW7Qza3UPivcUu_SmnW-XyUk9ez8

Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments”

https://arxiv.org/abs/1910.07224

Gaze360: Physically Unconstrained Gaze Estimation in the Wild
Kellnhofer et al.: https://arxiv.org/abs/1910.10088
Website : https://gaze360.csail.mit.edu
GitHub : https://github.com/Erkil1452/gaze360
#ArtificialIntelligence #DeepLearning #MachineLearning

Using machine learning and information visualisation for discovering latent topics in Twitter news
Vargas-Calderon et al.: https://arxiv.org/abs/1910.09114
#ArtificialIntelligence #MachineLearning #SocialNetworks

Quantum Supremacy Using a Programmable Superconducting Processor
Blog by John Martinis and Sergio Boixo : https://ai.googleblog.com/2019/10/quantum-supremacy-using-programmable.html
#QuantumComputer #QuantumPhysics #QuantumSupremacy

pdf: https://openaccess.thecvf.com/content_CVPR_2019/papers/Gu_Mask-Guided_Portrait_Editing_With_Conditional_GANs_CVPR_2019_paper.pdf

github repo: https://github.com/cientgu/Mask_Guided_Portrait_Editing

Generating Sequences With Recurrent Neural Networks
Paper: https://arxiv.org/pdf/1308.0850.pdf
This paper shows how Long Short-term Memory recurrent neural networks can be used to generate complex sequences with long-range structure, simply by predicting one data point at a time. The approach is demonstrated for text (where the data are discrete) and online handwriting (where the data are real-valued). It is then extended to handwriting synthesis by allowing the network to condition its predictions on a text sequence. The resulting system is able to generate highly realistic cursive handwriting in a wide variety of styles.