Search Results for author:
Found 43 papers, 23 papers with code
Neural Brain: A Neuroscience-inspired Framework for Embodied Agents
The rapid evolution of artificial intelligence (AI) has shifted from static, data-driven models to dynamic systems capable of perceiving and interacting with real-world environments.
Nature's Insight: A Novel Framework and Comprehensive Analysis of Agentic Reasoning Through the Lens of Neuroscience
In this work, we propose a novel neuroscience-inspired framework for agentic reasoning.
Evolutionary Reinforcement Learning for Interpretable Decision-Making in Supply Chain Management
To overcome this issue, in this work, we employ an Interpretable Artificial Intelligence (IAI) approach that combines evolutionary computation with Reinforcement Learning (RL) to generate interpretable decision-making policies in the form of decision trees.
Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages
An old-school recipe for training a classifier is to (i) learn a good feature extractor and (ii) optimize a linear layer atop.
2SSP: A Two-Stage Framework for Structured Pruning of LLMs
The second stage (Depth Pruning), instead, removes entire Attention submodules.
SMOSE: Sparse Mixture of Shallow Experts for Interpretable Reinforcement Learning in Continuous Control Tasks
SMOSE combines a set of interpretable decisionmakers, trained to be experts in different basic skills, and an interpretable router that assigns tasks among the experts.
Zeroth-Order Adaptive Neuron Alignment Based Pruning without Re-Training
Hence, we propose \textsc{NeuroAL}, a \emph{top-up} algorithm that can be used on top of any given pruning algorithm for LLMs, which modifies the block-wise and row-wise sparsity exploiting information from both the dense model and its sparse version to maximize the \emph{neuron alignment} among activations.
An investigation on the use of Large Language Models for hyperparameter tuning in Evolutionary Algorithms
Hyperparameter optimization is a crucial problem in Evolutionary Computation.
The Effect of Training Schedules on Morphological Robustness and Generalization
In this paper, we define various training schedules to specify how these variations are introduced during an evolutionary learning process.
Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems
Artificial intelligence methods are being increasingly applied across various domains, but their often opaque nature has raised concerns about accountability and trust.
Explainable artificial intelligence
Explainable Artificial Intelligence (XAI)
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Thanks to its simplicity and comparatively negligible computation, ZERO can serve as a strong baseline for future work in this field.
Influence Maximization in Hypergraphs using Multi-Objective Evolutionary Algorithms
Among the various methods for solving the IM problem, evolutionary algorithms (EAs) have been shown to be particularly effective.
MULTIFLOW: Shifting Towards Task-Agnostic Vision-Language Pruning
In this challenging setting, the transferable representations already encoded in the pretrained model are a key aspect to preserve.
Many-Objective Evolutionary Influence Maximization: Balancing Spread, Budget, Fairness, and Time
The Influence Maximization (IM) problem seeks to discover the set of nodes in a graph that can spread the information propagation at most.
Neuron-centric Hebbian Learning
To overcome this limitation, we propose a novel plasticity model, called Neuron-centric Hebbian Learning (NcHL), where optimization focuses on neuron- rather than synaptic-specific Hebbian parameters.
Social Interpretable Reinforcement Learning
(2) In the individual phase, then, each agent refines its individual performance by interacting with its own instance of the environment.
Understanding Sparse Neural Networks from their Topology via Multipartite Graph Representations
With these novelties, we show the following: (a) The proposed MGE allows to extract topological metrics that are much better predictors of the accuracy drop than metrics computed from current input-agnostic BGEs; (b) Which metrics are important at different sparsity levels and for different architectures; (c) A mixture of our topological metrics can rank PaI algorithms more effectively than Ramanujan-based metrics.
Self-building Neural Networks
We compare our proposed SBNN with traditional neural networks (NNs) over three classical control tasks from OpenAI.
Quality Diversity Evolutionary Learning of Decision Trees
Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI).
The emergence of division of labor through decentralized social sanctioning
Here we show that by introducing a model of social norms, which we regard as emergent patterns of decentralized social sanctioning, it becomes possible for groups of self-interested individuals to learn a productive division of labor involving all critical roles.
Reinforcement learning based adaptive metaheuristics
We demonstrate the applicability of this framework on two algorithms, namely Covariance Matrix Adaptation Evolution Strategies (CMA-ES) and Differential Evolution (DE), for which we learn, respectively, adaptation policies for the step-size (for CMA-ES), and the scale factor and crossover rate (for DE).
Online Distributed Evolutionary Optimization of Time Division Multiple Access Protocols
With the advent of cheap, miniaturized electronics, ubiquitous networking has reached an unprecedented level of complexity, scale and heterogeneity, becoming the core of several modern applications such as smart industry, smart buildings and smart cities.
Large-scale multi-objective influence maximisation with network downscaling
Finding the most influential nodes in a network is a computationally hard problem with several possible applications in various kinds of network-based problems.
Interpretable AI for policy-making in pandemics
For this reason, several works have applied machine learning techniques, often with the help of special-purpose simulators, to generate policies that were more effective than the ones obtained by governments.
Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs
However, they struggle when working with raw data, especially when the input dimensionality increases and the raw inputs alone do not give valuable insights on the decision-making process.
Graph-Aware Evolutionary Algorithms for Influence Maximization
Social networks represent nowadays in many contexts the main source of information transmission and the way opinions and actions are influenced.
Black-box adversarial attacks using Evolution Strategies
Several methods able to generate adversarial samples make use of gradients, which usually are not available to an attacker in real-world scenarios.
Seeking Quality Diversity in Evolutionary Co-design of Morphology and Control of Soft Tensegrity Modular Robots
Designing optimal soft modular robots is difficult, due to non-trivial interactions between morphology and controller.
A Signal-Centric Perspective on the Evolution of Symbolic Communication
The evolution of symbolic communication is a longstanding open research question in biology.
A Framework for Knowledge Integrated Evolutionary Algorithms
Notably, the KIEA framework is EA-agnostic (i. e., it works with any evolutionary algorithm), problem-independent (i. e., it is not dedicated to a specific type of problems), expandable (i. e., its knowledge base can grow over time).
Genetic Improvement of Routing Protocols for Delay Tolerant Networks
We apply this methodology, in silico, to six test cases of urban networks made of hundreds of nodes, and find that GI produces consistent gains in delivery probability in four cases.
Evolutionary learning of interpretable decision trees
We present a two-level optimization scheme that combines the advantages of evolutionary algorithms with the advantages of Q-learning.
Ranked #1 on
OpenAI Gym
on LunarLander-v2
EVO-RL: Evolutionary-Driven Reinforcement Learning
Furthermore, we propose that this distinction is decided by the evolutionary process, thus allowing evo-RL to be adaptive to different environments.
Distributed Embodied Evolution over Networks
In several network problems the optimum behavior of the agents (i. e., the nodes of the network) is not known before deployment.
Novelty Producing Synaptic Plasticity
A learning process with the plasticity property often requires reinforcement signals to guide the process.
Regularized Evolutionary Algorithm for Dynamic Neural Topology Search
Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i. e., network architectures) and is therefore memory expensive.
Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions
Hebbian learning is a biologically plausible mechanism for modeling the plasticity property in artificial neural networks (ANNs), based on the local interactions of neurons.
Learning with Delayed Synaptic Plasticity
Inspired by biology, plasticity can be modeled in artificial neural networks by using Hebbian learning rules, i. e. rules that update synapses based on the neuron activations and reinforcement signals.
Evaluating MAP-Elites on Constrained Optimization Problems
As such, it could be used in the future as an effective building-block for designing new constrained optimization algorithms.
Multi-Strategy Coevolving Aging Particle Optimization
We propose Multi-Strategy Coevolving Aging Particles (MS-CAP), a novel population-based algorithm for black-box optimization.
Distributed optimization in wireless sensor networks: an island-model framework
We perform extensive tests of different DOWSN configurations on a benchmark made up of continuous optimization problems; we analyze the influence of the network parameters (number of nodes, inter-node communication period and probability of accepting incoming solutions) on the optimization performance.
Compact Optimization Algorithms with Re-sampled Inheritance
The resulting compact algorithms with RI are tested on the CEC 2014 benchmark functions.
Limited Evaluation Cooperative Co-evolutionary Differential Evolution for Large-scale Neuroevolution
Many real-world control and classification tasks involve a large number of features.
