Tullio Facchinetti
Tag cloud
Picture wall
Daily
RSS Feed
  • RSS Feed
  • ATOM Feed
  • Daily Feed
Filters

Links per page

  • 20 links
  • 50 links
  • 100 links

Display

Filter untagged links
page 1 / 8
150 results tagged research  ✕
100-nlp-papers - 100 Must-Read NLP Papers https://github.com/mhagiwara/100-nlp-papers
Sat 05 Sep 2020 04:01:02 PM CEST
QRCode
collection list NLP paper research
Google 'BigBird' Achieves SOTA Performance on Long-Context NLP Tasks | Synced https://syncedreview.com/2020/08/03/google-bigbird-achieves-sota-performance-on-long-context-nlp-tasks/
Mon 03 Aug 2020 10:13:43 PM CEST
QRCode

BigBird is shown to dramatically improve performance across long-context NLP tasks, producing SOTA results in question answering and summarization.

article NLP research
DeepDream: How Alexander Mordvintsev Excavated the Computer’s Hidden Layers | The MIT Press Reader https://thereader.mitpress.mit.edu/deepdream-how-alexander-mordvintsev-excavated-the-computers-hidden-layers/
Mon 03 Aug 2020 10:10:41 PM CEST
QRCode

A Google researcher looks into the mind of a computer.

article deep_learning research tech
Why general artificial intelligence will not be realized | Humanities and Social Sciences Communications https://www.nature.com/articles/s41599-020-0494-4
Fri 10 Jul 2020 08:57:19 PM CEST
QRCode

The modern project of creating human-like artificial intelligence (AI) started after World War II, when it was discovered that electronic computers are not just number-crunching machines, but can also manipulate symbols. It is possible to pursue this goal without assuming that machine intelligence is identical to human intelligence. This is known as weak AI. However, many AI researcher have pursued the aim of developing artificial intelligence that is in principle identical to human intelligence, called strong AI. Weak AI is less ambitious than strong AI, and therefore less controversial. However, there are important controversies related to weak AI as well. This paper focuses on the distinction between artificial general intelligence (AGI) and artificial narrow intelligence (ANI). Although AGI may be classified as weak AI, it is close to strong AI because one chief characteristics of human intelligence is its generality. Although AGI is less ambitious than strong AI, there were critics almost from the very beginning. One of the leading critics was the philosopher Hubert Dreyfus, who argued that computers, who have no body, no childhood and no cultural practice, could not acquire intelligence at all. One of Dreyfus’ main arguments was that human knowledge is partly tacit, and therefore cannot be articulated and incorporated in a computer program. However, today one might argue that new approaches to artificial intelligence research have made his arguments obsolete. Deep learning and Big Data are among the latest approaches, and advocates argue that they will be able to realize AGI. A closer look reveals that although development of artificial intelligence for specific purposes (ANI) has been impressive, we have not come much closer to developing artificial general intelligence (AGI). The article further argues that this is in principle impossible, and it revives Hubert Dreyfus’ argument that computers are not in the world.

AI paper research
Why Sleep Deprivation Kills https://www.quantamagazine.org/why-sleep-deprivation-kills-20200604/
Wed 10 Jun 2020 01:43:56 AM CEST
QRCode

Going without sleep for too long kills animals but scientists haven’t known why. Newly published work suggests that the answer lies in an unexpected part of the body.

paper research
Unsupervised Translation of Programming Languages https://arxiv.org/abs/2006.03511
Wed 10 Jun 2020 01:34:08 AM CEST
QRCode

A transcompiler, also known as source-to-source translator, is a system that converts source code from a high-level programming language (such as C++ or Python) to another. Transcompilers are primarily used for interoperability, and to port codebases written in an obsolete or deprecated language (e.g. COBOL, Python 2) to a modern one. They typically rely on handcrafted rewrite rules, applied to the source code abstract syntax tree. Unfortunately, the resulting translations often lack readability, fail to respect the target language conventions, and require manual modifications in order to work properly. The overall translation process is timeconsuming and requires expertise in both the source and target languages, making code-translation projects expensive.
Although neural models significantly outperform their rule-based counterparts in the context of natural language translation, their applications to transcompilation have been limited due to the scarcity of parallel data in this domain. In this paper, we propose to leverage recent approaches in unsupervised machine translation to train a fully unsupervised neural transcompiler. We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy.
Our method relies exclusively on monolingual source code, requires no expertise in the source or target languages, and can easily be generalized to other
programming languages. We also build and release a test set composed of 852 parallel functions, along with unit tests to check the correctness of translations. We show that our model outperforms rule-based commercial baselines by a significant margin.

machine_learning neural_networks paper programming research
TESPy -j Thermal Engineering Systems in Python https://github.com/oemof/tespy
Thu 04 Jun 2020 12:16:26 PM CEST
QRCode

This package provides a powerful simulation toolkit for thermal engineering plants such as power plants, district heating systems or heat pumps.

coding_lang:python energy energy_efficiency opensource research simulation source_code
GIMP-ML - Set of Machine Learning Python plugins for GIMP https://github.com/kritiksoman/GIMP-ML/blob/master/README.md
Sun 10 May 2020 04:34:34 PM CEST
QRCode

image

graphics neural_networks opensource research software source_code
cli-arxiv - CLI tool for exploring arXiv https://github.com/knguyenanhoa/cli-arxiv
Sat 02 May 2020 12:46:32 AM CEST
QRCode

CLI tool for exploring arXiv (inspired by karpathy's brilliant ArXiv Sanity Preserver)

The script will create data/pdf/, data/txt/ and data/summary/ directories to hold files downloaded from arXiv. I am also aware that this is a rather stupid way to implement a datastore but DBs seem a bit over the top. Text from PDFs are auto-converted on downloaded and are used to suggest future articles to the user. Downloading articles is idempotent.

#cli-app browser opensource research science search software source_code tools
Zenodo https://about.zenodo.org/
Wed 29 Apr 2020 11:06:14 PM CEST
QRCode

Zenodo is a free and open digital archive built by CERN and OpenAIRE, enabling researchers to share and preserve research output in any size, format and from all fields of research.

data online platform research science service sharing webservice
The Illustrated FixMatch for Semi-Supervised Learning https://amitness.com/2020/03/fixmatch-semi-supervised/
Fri 03 Apr 2020 09:24:52 PM CEST
QRCode

Deep Learning has shown very promising results in the field of Computer Vision. But when applying it to practical domains such as medical imaging, lack of labeled data is a major challenge.

In practical settings, labeling data is a time consuming and expensive process. Though, you have a lot of images, only a small portion of them can be labeled due to resource constraints. In such settings, how can we leverage the remaining unlabeled images along with the labeled images to improve the performance of our model? The answer is semi-supervised learning.

FixMatch is a recent semi-supervised approach by Sohn et al. from Google Brain that improved the state of the art in semi-supervised learning(SSL). It is a simpler combination of previous methods such as UDA and ReMixMatch. In this post, we will understand the concept of FixMatch and also see how it got 78% median accuracy and 84% maximum accuracy on CIFAR-10 with just 10 labeled images.

article machine_learning research science techniques
Gherkin Reference https://cucumber.io/docs/gherkin/reference/
Tue 17 Mar 2020 02:23:49 PM CET
QRCode

Gherkin uses a set of special keywords to give structure and meaning to executable specifications. Each keyword is translated to many spoken languages; in this reference we’ll use English.

language research tech testing
CSL research team develops voice localization techniques for smart speakers https://csl.illinois.edu/news/csl-research-team-develops-voice-localization-techniques-smart-speakers
Tue 17 Mar 2020 08:25:53 AM CET
QRCode

VoLoc, a system that uses the microphone array on Alexa, as well as room echoes of the human voice, to infer the user location inside the home.

image

article embedded localization paper research sound
CSolve: Liquid Types-Based Verifier for C https://goto.ucsd.edu/csolve/
Sat 14 Mar 2020 09:46:53 PM CET
QRCode
c programming research
The Fortran 77 codes for the open-loop and the closed-loop simulations for the Tennessee Eastman process (TEP). https://github.com/camaramm/tennessee-eastman-profBraatz
Wed 11 Mar 2020 10:55:57 PM CET
QRCode

The Fortran 77 codes for the open-loop and the closed-loop simulations for the Tennessee Eastman process (TEP) as well as the training and testing data files used for evaluating the data-driven methods (PCA, PLS, FDA, and CVA).

automation coding_lang:fortran dataset research simulation software
Up to two billion times acceleration of scientific simulations with deep neural architecture search https://arxiv.org/abs/2001.08055
Fri 24 Jan 2020 05:17:46 AM CET
QRCode

Computer simulations are invaluable tools for scientific discovery. However, accurate simulations are often slow to execute, which limits their applicability to extensive parameter exploration, large-scale data analysis, and uncertainty quantification. A promising route to accelerate simulations by building fast emulators with machine learning requires large training datasets, which can be prohibitively expensive to obtain with slow simulations. Here we present a method based on neural architecture search to build accurate emulators even with a limited number of training data. The method successfully accelerates simulations by up to 2 billion times in 10 scientific cases including astrophysics, climate science, biogeochemistry, high energy density physics, fusion energy, and seismology, using the same super-architecture, algorithm, and hyperparameters. Our approach also inherently provides emulator uncertainty estimation, adding further confidence in their use. We anticipate this work will accelerate research involving expensive simulations, allow more extensive parameters exploration, and enable new, previously unfeasible computational discovery.

deep_learning neural_networks open_access optimization paper research simulation
A distributional code for value in dopamine-based reinforcement learning https://www.nature.com/articles/s41586-019-1924-6
Sat 18 Jan 2020 04:47:05 AM CET
QRCode

Analyses of single-cell recordings from mouse ventral tegmental area are consistent with a model of reinforcement learning in which the brain represents possible future rewards not as a single mean of stochastic outcomes, as in the canonical model, but instead as a probability distribution.

algorithm article machine_learning neural_networks research
Using neural networks to solve advanced mathematics equations https://ai.facebook.com/blog/using-neural-networks-to-solve-advanced-mathematics-equations/
Wed 15 Jan 2020 05:01:31 PM CET
QRCode

Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.

AI article math neural_networks post research science
Quantum teleportation http://www.bris.ac.uk/news/2019/december/quantum-teleportation.html
Fri 03 Jan 2020 02:38:58 PM CET
QRCode

In one of the breakthrough experiments, researchers at the University of Bristol’s Quantum Engineering Technology Labs (QET Labs) demonstrate the quantum teleportation of information between two programmable chip for the first time, which they remark is a cornerstone of quantum communications and quantum computing.

Quantum teleportation offers quantum state transfer of a quantum particle from one place to another by utilising entanglement. Teleportation is not only useful for quantum communication but is a fundamental building-block of optical quantum computing. Establishing an entangled communication link between two chips in the lab however has proven to be highly challenging.

“Each chip was then fully programmed to perform a range of demonstrations which utilise the entanglement.

“The flagship demonstration was a two-chip teleportation experiment, whereby the individual quantum state of a particle is transmitted across the two chips after a quantum measurement is performed. This measurement utilises the strange behaviour of quantum physics, which simultaneously collapses the entanglement link and transfers the particle state to another particle already on the receiver chip.”

article communication computer quantum research
A soft robotic insect that survives being flattened by a fly swatter https://actu.epfl.ch/news/a-soft-robotic-insect-that-survives-being-flattene/
Fri 03 Jan 2020 02:26:58 PM CET
QRCode

Researchers at EPFL have developed an ultra-light robotic insect that uses its soft artificial muscles to move at 3 cm per second across different types of terrain. It can be folded or crushed and yet continue to move.

image

article research robotics
page 1 / 8
3651 links
Shaarli - The personal, minimalist, super-fast, database free, bookmarking service by the Shaarli community - Theme by kalvn