15,241 research outputs found
Learning Rotation-Agnostic Representations via Group Equivariant VAEs
No full textAn emerging field in representation learning involves the study of group-equivariant neural networks, that leverage concepts from group representation theory to design neural architectures that can exploit discrete and continuous symmetries to produce more general representations. Following this direction, in this work we demonstrate how an image embedding agnostic to rotations can be naturally obtained by training a variational autoencoder (S-GVAE) equipped with a Group equivariant Convolutional Neural Network (G-CNN) encoder
OLIVAW: Mastering Othello without Human Knowledge, nor a Penny
No full textWe introduce OLIVAW, an AI Othello player adopting the design principles of the famous AlphaGo programs. The main motivation behind OLIVAW was to attain exceptional competence in a non-trivial board game at a tiny fraction of the cost of its illustrious predecessors. In this paper, we show how the AlphaGo Zero's paradigm can be successfully applied to the popular game of Othello using only commodity hardware and free cloud services. While being simpler than Chess or Go, Othello maintains a considerable search space and difficulty in evaluating board positions. To achieve this result, OLIVAW implements some improvements inspired by recent works to accelerate the standard AlphaGo Zero learning process. The main modification implies doubling the positions collected per game during the training phase, by including also positions not played but largely explored by the agent. We tested the strength of OLIVAW in three different ways: by pitting it against Edax, the strongest open-source Othello engine, by playing anonymous games on the web platform OthelloQuest, and finally in two in-person matches against top-notch human players: a national champion and a former world champion
Artificial scientific discovery
No full textRooted in the explosion of deep learning over the past decade, this thesis spans from AlphaGo to ChatGPT to empirically examine the fundamental concepts needed to realize the vision of an artificial scientist: a machine with the capacity to autonomously generate original research and contribute to the expansion of human knowledge.
The investigation begins with {\sc Olivaw}, an AlphaGo Zero-like agent that discovers Othello knowledge from scratch but is unable to communicate it. This realization leads to the development of the Explanatory Learning (EL) framework, a formalization of the problem faced by a scientist when trying to explain a new phenomenon to their peers. The effective EL prescriptions allow us to crack Zendo, a board game simulating the scientific endeavor. This success comes with a fundamental insight: an artificial scientist must develop its own interpretation of the language used to explain its findings. This perspective then leads us to see modern multimodal models as interpreters, and to devise a new way to build interpretable and cost-effective CLIP-like models: by coupling two unimodal models using little multimodal data and no further training.
Finally, we discuss what ChatGPT and its siblings are still missing to become artificial scientists, and introduce Odeen, a benchmark about interpreting explanations that sees LLMs going no further than random chance while being instead fully solved by humans
Declaration of Intention for Antonio Franchihtti
No full textDeclaration of Intention to become a citizen of the United States, as filled out and signed by Antonio Franchitti. Applicant lists himself as a 47 year old farmer residing in Hammonton, New Jersey, born in Campombosso, Italy on 18 April 1870, who sailed on the US bound vessel Britania. Declaration submitted and sworn April 21, 1917
The role of educative thought in the life and work of Antonio Gramsci
No full textMany philosophers have propounded a vision of an improved society, what distinguishes Antonio Gramsci is his continuous effort to make it happen by understanding the process in order to put into practice. Gramsci's conviction about the importance of educative development came from both theory and experience. While there has been considerable examination of Gramsci's work in relation to the Prison Notebooks, this study will seek to address a lacuna in Gramsci scholarship. Using Gramsci's philological method, I analyse Gramsci's pre-prison activity; his pre-prison articles and letters, which, together with his letters from prison, formed part of his educative mission. This educative process was necessary, in order to construct a new party which would develop a collective will, collaboratively, with the masses.In this study therefore, I explore the contexts and formative experiences of the first part of his life together with the intellectual sources from which Gramsci developed his later theories, making central hitherto underemphasised connections between them which informed his writing and ideas. I intend to illustrate that Gramsci's underlying purpose in his writing, and political activity, was not only practical, on how to create a new socialist ruling class, but also educative in forming the mindset and values of his comrades. So that in addition to outlining his vision of a new order, he implicitly guided or explicitly explained the processes by which the necessary changes in social relations and moral climate could be made in order to achieve it. Each person had to engage with the values of the new order so that each could contribute to the construction of a new robust state. It was essential to build a hegemony at the most profound level, one which was dependent on collective understandings and a collective will
Variazioni sul tema del 'sostituzionismo'
No full textStarting from a controversial passage of the ‘Epistle of Barnabas’ (IV,6), this paper aims at demonstrating: a) that the reading offered by Codex Sinaiticus (א) is supported by morphology and syntax, as well as by the historical context the ‘Letter of Barnabas’ comes from; b) that the dispute about the 'covenant' regards Judaism, better then judaizing Christians
Edna Ferber in St. Anthony Hotel, San Antonio, Tex., 1948
No full text''Ferber's novel, Giant, set on a fictitious south Texas ranch, was published in 1952.''''Edna Ferber was in San Antonio on Saturday for a search of the surrounding ranch country for material and characters for a new book. The author of Show boat was registered at the St. Anthony Hotel.'
Desenganos mysticos para as almas detidas ou enganadas no caminho da perfeiçao... : seu author na lingua hespanhola... Fr. Antonio Arbiol...
No full textSign.: [parágrafo]-2[parágrafo]8, 3[parágrafo]2, A-Z8, 2A-2X8, 2Z1. -- Texto a dos col. -- Port. con viñeta tip. -- Falto de p. 305-350.Sainz Rodrígue
Relative representations enable zero-shot latent space communication
No full textNeural networks embed the geometric structure of a data manifold lying in a
high-dimensional space into latent representations. Ideally, the distribution
of the data points in the latent space should depend only on the task, the
data, the loss, and other architecture-specific constraints. However, factors
such as the random weights initialization, training hyperparameters, or other
sources of randomness in the training phase may induce incoherent latent spaces
that hinder any form of reuse. Nevertheless, we empirically observe that, under
the same data and modeling choices, the angles between the encodings within
distinct latent spaces do not change. In this work, we propose the latent
similarity between each sample and a fixed set of anchors as an alternative
data representation, demonstrating that it can enforce the desired invariances
without any additional training. We show how neural architectures can leverage
these relative representations to guarantee, in practice, invariance to latent
isometries and rescalings, effectively enabling latent space communication:
from zero-shot model stitching to latent space comparison between diverse
settings. We extensively validate the generalization capability of our approach
on different datasets, spanning various modalities (images, text, graphs),
tasks (e.g., classification, reconstruction) and architectures (e.g., CNNs,
GCNs, transformers).Comment: ICLR 2023 notable top 5%, 26 pages, 11 figures, 18 table
Antonio Rosminis Principles of moral science: translation of an Italian philosophical work to Portuguese
No full textEste trabalho se compõe de duas partes. Primeiramente, um estudo introdutório sobre o autor, Antonio Rosmini, sobre sua obra filosófica e, mais especificamente, sobre o livro Principi della scienza morale, que, na segunda parte, traduzimos para o português. Na introdução, expomos brevemente o sistema filosófico rosminiano e o contextualizamos no âmbito histórico-filosófico. Além disso, apresentamos o percurso por nós desenvolvido para obter uma tradução filologicamente correta do texto original, incluindo um breve glossário dos termos filosóficos empregados pelo autor.This work is composed of two parts. Firstly, there is an introductoty study on the author, Antonio Rosmini, on his phylosophical system and, more specifically, on the book Principi della scienza morale, which we have translated to Portuguese, in the second part. In the introduction, we expose briefly the rosminian phylosofical system and we place it in its historical-phylosofical context. Furthermore, we show the path weve followed to reach a phylologically correct translation from the original text, including a brief glossary of phylosophical terms employed by the author
- …
