Search Results for author:
Found 60 papers, 11 papers with code
Clue-Instruct: Text-Based Clue Generation for Educational Crossword Puzzles
By gathering from Wikipedia pages informative content associated with relevant keywords, we use Large Language Models to automatically generate pedagogical clues related to the given input keyword and its context.
Multitask Kernel-based Learning with Logic Constraints
This paper presents a general framework to integrate prior knowledge in the form of logic constraints among a set of task functions into kernel machines.
On the Resurgence of Recurrent Models for Long Sequences -- Survey and Research Opportunities in the Transformer Era
A longstanding challenge for the Machine Learning community is the one of developing models that are capable of processing and learning from very long sequences of data.
Nature-Inspired Local Propagation
The spectacular results achieved in machine learning, including the recent advances in generative AI, rely on large data collections.
Neural Time-Reversed Generalized Riccati Equation
This paper introduces a novel neural-based approach to optimal control, with the aim of working forward-in-time.
ArabIcros: AI-Powered Arabic Crossword Puzzle Generation for Educational Applications
This paper presents the first Arabic crossword puzzle generator driven by advanced AI technology.
The WebCrow French Crossword Solver
Crossword puzzles are one of the most popular word games, played in different languages all across the world, where riddle style can vary significantly from one country to another.
Italian Crossword Generator: Enhancing Education through Interactive Word Puzzles
On the other hand, for generating crossword clues from a given text, Zero/Few-shot learning techniques were used to extract clues from the input text, adding variety and creativity to the puzzles.
Multitask Kernel-based Learning with First-Order Logic Constraints
In this paper we propose a general framework to integrate supervised and unsupervised examples with background knowledge expressed by a collection of first-order logic clauses into kernel machines.
Graph Neural Networks for Topological Feature Extraction in ECG Classification
While ECG situations have numerous similarities, little attention has been paid to categorizing ECGs using graph neural networks.
Collectionless Artificial Intelligence
By and large, the professional handling of huge data collections is regarded as a fundamental ingredient of the progress of machine learning and of its spectacular results in related disciplines, with a growing agreement on risks connected to the centralization of such data collections.
Continual Learning with Pretrained Backbones by Tuning in the Input Space
The intrinsic difficulty in adapting deep learning models to non-stationary environments limits the applicability of neural networks to real-world tasks.
PARTIME: Scalable and Parallel Processing Over Time with Deep Neural Networks
nature of the streamed data with samples that are smoothly evolving over time for efficient gradient computations.
Learning to Identify Drilling Defects in Turbine Blades with Single Stage Detectors
The application is challenging due to the large image resolutions in which defects are very small and hardly captured by the commonly used anchor sizes, and also due to the small size of the available dataset.
Deep Learning to See: Towards New Foundations of Computer Vision
The remarkable progress in computer vision over the last few years is, by and large, attributed to deep learning, fueled by the availability of huge sets of labeled data, and paired with the explosive growth of the GPU paradigm.
Knowledge-driven Active Learning
The deployment of Deep Learning (DL) models is still precluded in those contexts where the amount of supervised data is limited.
Logic Constraints to Feature Importances
In recent years, Artificial Intelligence (AI) algorithms have been proven to outperform traditional statistical methods in terms of predictivity, especially when a large amount of data was available.
Clustering-Based Interpretation of Deep ReLU Network
Amongst others, the adoption of Rectified Linear Units (ReLUs) is regarded as one of the ingredients of the success of deep learning.
Can machines learn to see without visual databases?
This paper sustains the position that the time has come for thinking of learning machines that conquer visual skills in a truly human-like context, where a few human-like object supervisions are given by vocal interactions and pointing aids only.
Graph Neural Networks for Graph Drawing
Graph Drawing techniques have been developed in the last few years with the purpose of producing aesthetically pleasing node-link layouts.
Messing Up 3D Virtual Environments: Transferable Adversarial 3D Objects
In the last few years, the scientific community showed a remarkable and increasing interest towards 3D Virtual Environments, training and testing Machine Learning-based models in realistic virtual worlds.
Logic Explained Networks
The language used to communicate the explanations must be formal enough to be implementable in a machine and friendly enough to be understandable by a wide audience.
Friendly Training: Neural Networks Can Adapt Data To Make Learning Easier
In the last decade, motivated by the success of Deep Learning, the scientific community proposed several approaches to make the learning procedure of Neural Networks more effective.
Entropy-based Logic Explanations of Neural Networks
Explainable artificial intelligence has rapidly emerged since lawmakers have started requiring interpretable models for safety-critical domains.
Ranked #1 on
Image Classification
on CUB
An Optimal Control Approach to Learning in SIDARTHE Epidemic model
We formulate the problem in terms of a functional risk that depends on the learning variables through the solutions of a dynamic system.
Gravitational Models Explain Shifts on Human Visual Attention
Another where the information from these maps is merged in order to select a single location to be attended for further and more complex computations and reasoning.
Developing Constrained Neural Units Over Time
In this paper we present a foundational study on a constrained method that defines learning problems with Neural Networks in the context of the principle of least cognitive action, which very much resembles the principle of least action in mechanics.
SAILenv: Learning in Virtual Visual Environments Made Simple
Recently, researchers in Machine Learning algorithms, Computer Vision scientists, engineers and others, showed a growing interest in 3D simulators as a mean to artificially create experimental settings that are very close to those in the real world.
Wave Propagation of Visual Stimuli in Focus of Attention
Fast reactions to changes in the surrounding visual environment require efficient attention mechanisms to reallocate computational resources to most relevant locations in the visual field.
Focus of Attention Improves Information Transfer in Visual Features
In order to better structure the input probability distribution, we use a human-like focus of attention model that, coherently with the information maximization model, is also based on second-order differential equations.
Domain Knowledge Alleviates Adversarial Attacks in Multi-Label Classifiers
Adversarial attacks on machine learning-based classifiers, along with defense mechanisms, have been widely studied in the context of single-label classification problems.
Graph Neural Networks Meet Neural-Symbolic Computing: A Survey and Perspective
Neural-symbolic computing has now become the subject of interest of both academic and industry research laboratories.
Local Propagation in Constraint-based Neural Network
In this paper we study a constraint-based representation of neural network architectures.
A Lagrangian Approach to Information Propagation in Graph Neural Networks
GNNs exploit a set of state variables, each assigned to a graph node, and a diffusion mechanism of the states among neighbor nodes, to implement an iterative procedure to compute the fixed point of the (learnable) state transition function.
Toward Improving the Evaluation of Visual Attention Models: a Crowdsourcing Approach
A computational modeling of this phenomenon must take into account where people look in order to evaluate which are the salient locations (spatial distribution of the fixations), when they look in those locations to understand the temporal development of the exploration (temporal order of the fixations), and how they move from one location to another with respect to the dynamics of the scene and the mechanics of the eyes (dynamics).
Relational Neural Machines
Deep learning has been shown to achieve impressive results in several tasks where a large amount of training data is available.
Backprop Diffusion is Biologically Plausible
The Backpropagation algorithm relies on the abstraction of using a neural model that gets rid of the notion of time, since the input is mapped instantaneously to the output.
Discrete and Continuous Deep Residual Learning Over Graphs
In this paper we propose the use of continuous residual modules for graph kernels in Graph Neural Networks.
Jointly Learning to Detect Emotions and Predict Facebook Reactions
In this paper we focus on Facebook posts paired with reactions of multiple users, and we investigate their relationships with classes of emotions that are typically considered in the task of emotion detection.
Learning Visual Features Under Motion Invariance
Humans are continuously exposed to a stream of visual data with a natural temporal structure.
T-Norms Driven Loss Functions for Machine Learning
Neural-symbolic approaches have recently gained popularity to inject prior knowledge into a learner without requiring it to induce this knowledge from data.
On the relation between Loss Functions and T-Norms
Deep learning has been shown to achieve impressive results in several domains like computer vision and natural language processing.
On the Role of Time in Learning
By and large the process of learning concepts that are embedded in time is regarded as quite a mature research topic.
Spatiotemporal Local Propagation
This paper proposes an in-depth re-thinking of neural computation that parallels apparently unrelated laws of physics, that are formulated in the variational framework of the least action principle.
Least Action Principles and Well-Posed Learning Problems
Machine Learning algorithms are typically regarded as appropriate optimization schemes for minimizing risk functions that are constructed on the training set, which conveys statistical flavor to the corresponding learning problem.
Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning
In spite of the recent impact of AI, several works have identified the need for principled knowledge representation and reasoning mechanisms integrated with deep learning-based systems to provide sound and explainable models for such systems.
LYRICS: a General Interface Layer to Integrate Logic Inference and Deep Learning
In spite of the amazing results obtained by deep learning in many applications, a real intelligent behavior of an agent acting in a complex environment is likely to require some kind of higher-level symbolic inference.
Typed Graph Networks
To illustrate the generality of the original model, we present a Graph Neural Network formalisation, which partitions the vertices of a graph into a number of types.
Integrating Learning and Reasoning with Deep Logic Models
Deep learning is very effective at jointly learning feature representations and classification models, especially when dealing with high dimensional input patterns.
Cognitive Action Laws: The Case of Visual Features
A special choice of the functional index, which leads to forth-order differential equations---Cognitive Action Laws (CAL)---exhibits a structure that mirrors classic formulation of machine learning.
Backpropagation and Biological Plausibility
This might open the doors to a truly novel class of learning algorithms where, because of the introduction of the notion of support neurons, the optimization scheme also plays a fundamental role in the construction of the architecture.
Learning Neuron Non-Linearities with Kernel-Based Deep Neural Networks
The effectiveness of deep neural architectures has been widely supported in terms of both experimental and foundational principles.
Constraint-Based Visual Generation
We use deep architectures to model the involved variables, and propose a computational scheme where the learning process carries out a satisfaction of the constraints.
Generalization in quasi-periodic environments
By and large the behavior of stochastic gradient is regarded as a challenging problem, and it is often presented in the framework of statistical machine learning.
Motion Invariance in Visual Environments
The puzzle of computer vision might find new challenging solutions when we realize that most successful methods are working at image level, which is remarkably more difficult than processing directly visual streams, just as happens in nature.
Convolutional Networks in Visual Environments
Basically, while the theory enables the implementation of novel computer vision systems, it is also provides an intriguing explanation of the solution that evolution has discovered for humans, where it looks like that the video blurring in newborns and the day-night rhythm seem to emerge in a general computational framework, regardless of biology.
Variational Laws of Visual Attention for Dynamic Scenes
We devise variational laws of the eye-movement that rely on a generalized view of the Least Action Principle in physics.
Ranked #1 on
Saliency Detection
on CAT2000
The principle of cognitive action - Preliminary experimental analysis
In this document we shows a first implementation and some preliminary results of a new theory, facing Machine Learning problems in the frameworks of Classical Mechanics and Variational Calculus.
Collapsing of dimensionality
We analyze a new approach to Machine Learning coming from a modification of classical regularization networks by casting the process in the time dimension, leading to a sort of collapse of dimensionality in the problem of learning the model parameters.
Learning to see like children: proof of concept
In the last few years we have seen a growing interest in machine learning approaches to computer vision and, especially, to semantic labeling.
