Search Results for author:
Found 19 papers, 0 papers with code
A Gentle Introduction to Deep Nets and Opportunities for the Future
The first half of this tutorial will make deep nets more accessible to a broader audience, following “Deep Nets for Poets” and “A Gentle Introduction to Fine-Tuning.” We will also introduce GFT (general fine tuning), a little language for fine tuning deep nets with short (one line) programs that are as easy to code as regression in statistics packages such as R using glm (general linear models).
Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problems
This report describes a test of the large language model GPT-4 with the Wolfram Alpha and the Code Interpreter plug-ins on 105 original problems in science and math, at the high school and college levels, carried out in June-August 2023.
Benchmarks for Automated Commonsense Reasoning: A Survey
We discuss the gaps in the existing benchmarks and aspects of commonsense reasoning that are not addressed in any existing benchmark.
Mathematics, word problems, common sense, and artificial intelligence
The paper discusses the capacities and limitations of current artificial intelligence (AI) technology to solve word problems that combine elementary knowledge with commonsense reasoning.
Limits of an AI program for solving college math problems
Drori et al. (2022) report that "A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level ... [It] automatically answers 81\% of university-level mathematics problems."
A very preliminary analysis of DALL-E 2
The DALL-E 2 system generates original synthetic images corresponding to an input text as caption.
Pragmatic constraints and pronoun reference disambiguation: the possible and the impossible
Pronoun disambiguation in understanding text and discourse often requires the application of both general pragmatic knowledge and context-specific information.
Physical Reasoning in an Open World
Most work on physical reasoning, both in artificial intelligence and in cognitive science, has focused on closed-world reasoning, in which it is assumed that the problem specification specifies all relevant objects and substance, all their relations in an initial situation, and all exogenous events.
The Defeat of the Winograd Schema Challenge
The Winograd Schema Challenge - a set of twin sentences involving pronoun reference disambiguation that seem to require the use of commonsense knowledge - was proposed by Hector Levesque in 2011.
Deep Learning and Mathematical Intuition: A Review of (Davies et al. 2021)
A recent paper by Davies et al (2021) describes how deep learning (DL) technology was used to find plausible hypotheses that have led to two original mathematical results: one in knot theory, one in representation theory.
A Flawed Dataset for Symbolic Equation Verification
Arabshahi, Singh, and Anandkumar (2018) propose a method for creating a dataset of symbolic mathematical equations for the tasks of symbolic equation verification and equation completion.
Unanswerable Questions about Images and Texts
Questions about a text or an image that cannot be answered raise distinctive issues for an AI.
The test set for the TransCoder system
The TransCoder system translates source code between Java, C++, and Python 3.
A Review of Winograd Schema Challenge Datasets and Approaches
The Winograd Schema Challenge is both a commonsense reasoning and natural language understanding challenge, introduced as an alternative to the Turing test.
The Use of Deep Learning for Symbolic Integration: A Review of (Lample and Charton, 2019)
Lample and Charton (2019) describe a system that uses deep learning technology to compute symbolic, indefinite integrals, and to find symbolic solutions to first- and second-order ordinary differential equations, when the solutions are elementary functions.
Winograd Schemas and Machine Translation
A Winograd schema is a pair of sentences that differ in a single word and that contain an ambiguous pronoun whose referent is different in the two sentences and requires the use of commonsense knowledge or world knowledge to disambiguate.
The Scope and Limits of Simulation in Cognitive Models
It has been proposed that human physical reasoning consists largely of running "physics engines in the head" in which the future trajectory of the physical system under consideration is computed precisely using accurate scientific theories.
The Limitations of Standardized Science Tests as Benchmarks for Artificial Intelligence Research: Position Paper
In particular, standardized tests do not test knowledge that is obvious for people; none of this knowledge can be assumed in AI systems.
The Relevance of Proofs of the Rationality of Probability Theory to Automated Reasoning and Cognitive Models
A number of well-known theorems, such as Cox's theorem and de Finetti's theorem.
