BigBird is shown to dramatically improve performance across long-context NLP tasks, producing SOTA results in question answering and summarization.
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.
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.
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.
This package provides a powerful simulation toolkit for thermal engineering plants such as power plants, district heating systems or heat pumps.
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.
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.
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.
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.
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.
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).
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.
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.
Facebook AI has developed the first neural network that uses symbolic reasoning to solve advanced mathematics problems.
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.”
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.