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.

Deep learning might not be an end solution for all the problems, but it isn't going away soon.
"deep learning must be augmented with some operations borrowed from classical symbolic systems, which is to say we need hybrid models, which take the best of classical AI (which allows for explicit representation of hierachical structure and abstract rules) and combine that with the strengths of deep learning." - Gary Marcus
Blog: https://medium.com/@GaryMarcus/bengio-v-marcus-and-the-past-present-and-future-of-neural-network-models-of-language-b4f795ff352b
Further reading: https://arxiv.org/pdf/1810.08272.pdf

Deep learning algorithm helps diagnose neurological emergencies
https://physicsworld.com/a/deep-learning-algorithm-helps-diagnose-neurological-emergencies/

Anatomy of Matplotlib
Tutorial developed for the SciPy conference : https://github.com/matplotlib/AnatomyOfMatplotlib
#Matplotlib #DataScience #DeepLearning

Learning Partial Differential Equations from Data Using Neural Networks
Hasan et al.: https://arxiv.org/abs/1910.10262
#DifferentialEquations #MachineLearning #NeuralNetworks

An article in le figaro on the occasion of the release of Yann LeCun book.

https://www.lefigaro.fr/vox/economie/charles-jaigu-ce-que-l-ia-dit-de-notre-cerveau-20191023

AI Benchmark: All About Deep Learning on Smartphones in 2019
https://arxiv.org/abs/1910.06663