3 citations · 4 across the 15 of their papers we have counts for
17 papers
Runtime-Incremental Transformer for Reinforcement-Learning-Based Adaptive Control
Giansalvo Cirrincione, Adriano Fagiolini
Learning-based adaptive control of robotic manipulators with non-observable friction memory has been addressed by attention- based meta-controllers whose number of attention heads…
Hierarchical Soft Actor-Critic for Sparse-Reward Long-Horizon Reinforcement Learning
Zahra Abdalla Elashaal, Afef Hfaiedh, Nahla Khraief +2
Exploration in sparse-reward long-horizon tasks poses significant challenges for reinforcement learning. To address these challenges, we propose a two-level Hierarchical Reinforcem…
When is the combined load identifiable from a stress-intensity profile? A coupled forward-inverse study on SIFBench finite-element data
Giansalvo Cirrincione, Filippo Grassia
This work studies the inverse problem of recovering the relative magnitudes of the tension, bending, and bearing loads acting on a crack from its stress-intensity-factor profile al…
Incremental Transformer for Surrogate-Based Inverse Design of Geopolymer Mixtures
Giansalvo Cirrincione, Filippo Grassia
Small-data inverse design is challenging in engineering informatics when observations are heterogeneous, mixed-type, and constrained by physical relations among design variables. T…
Learned Lyapunov Shielding for Adaptive Control
Giansalvo Cirrincione, Adriano Fagiolini
We augment the Slotine--Li adaptive controller for Euler--Lagrange systems with three learned components: a structured-quadratic Lyapunov function \(V_ψ\) whose positive-definitene…
Temporal Attention for Adaptive Control of Euler-Lagrange Systems with Unobservable Memory
Giansalvo Cirrincione, Adriano Fagiolini
Adaptive control of Euler-Lagrange systems is challenging when friction is governed by a finite-horizon internal state that is not directly observable from joint measurements. In t…
Rank, Head-Channel Non-Identifiability, and Symmetry Breaking: A Precise Analysis of Representational Collapse in Transformers
Giansalvo Cirrincione
A widely cited result by Dong et al. (2021) showed that Transformers built from self-attention alone, without skip connections or feed-forward layers, suffer from rapid rank collap…
INCRT: An Incremental Transformer That Determines Its Own Architecture
Giansalvo Cirrincione
Transformer architectures are designed by trial and error: the number of attention heads, the depth, and the head size are fixed before training begins, with no mathematical princi…
Hierarchical Kernel Transformer: Multi-Scale Attention with an Information-Theoretic Approximation Analysis
Giansalvo Cirrincione
The Hierarchical Kernel Transformer (HKT) is a multi-scale attention mechanism that processes sequences at L resolution levels via trainable causal downsampling, combining level-sp…
On the Geometry of Positional Encodings in Transformers
Giansalvo Cirrincione
Neural language models process sequences of words, but the mathematical operations inside them are insensitive to the order in which words appear. Positional encodings are the comp…
Collapse-Free Prototype Readout Layer for Transformer Encoders
Giansalvo Cirrincione, Rahul Ranjeev Kumar
DDCL-Attention is a prototype-based readout layer for transformer encoders that replaces simple pooling methods, such as mean pooling or class tokens, with a learned compression me…
DDCL-INCRT: A Self-Organising Transformer with Hierarchical Prototype Structure (Theoretical Foundations)
Giansalvo Cirrincione
Modern neural networks of the transformer family require the practitioner to decide, before training begins, how many attention heads to use, how deep the network should be, and ho…
DDCL: Deep Dual Competitive Learning: A Differentiable End-to-End Framework for Unsupervised Prototype-Based Representation Learning
Giansalvo Cirrincione
A persistent structural weakness in deep clustering is the disconnect between feature learning and cluster assignment. Most architectures invoke an external clustering step, typica…
The geometry of BERT
Matteo Bonino, Giorgia Ghione, Giansalvo Cirrincione
Transformer neural networks, particularly Bidirectional Encoder Representations from Transformers (BERT), have shown remarkable performance across various tasks such as classificat…
Vision Transformer for femur fracture classification
Leonardo Tanzi, Andrea Audisio, Giansalvo Cirrincione +2
In recent years, the scientific community has focused on the development of CAD tools that could improve bone fractures' classification, mostly based on Convolutional Neural Networ…
Gradient-based Competitive Learning: Theory
Giansalvo Cirrincione, Pietro Barbiero, Gabriele Ciravegna +1
Deep learning has been widely used for supervised learning and classification/regression problems. Recently, a novel area of research has applied this paradigm to unsupervised task…
Topological Gradient-based Competitive Learning
Pietro Barbiero, Gabriele Ciravegna, Vincenzo Randazzo +1
Topological learning is a wide research area aiming at uncovering the mutual spatial relationships between the elements of a set. Some of the most common and oldest approaches invo…