Research Papers
The cutting edge of artificial intelligence research. Sharded from the global knowledge mesh.
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2010.06746
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2010.09280
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2010.11328
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2010.13309
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2010.14894
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2011.01926
Structural intelligence indexing in progress...
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2011.05081
Many real-world optimization problems have multiple interacting components. Each of these can be NP-hard and they can be
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2011.06551
Boolean satisfiability is a propositional logic problem of interest in multiple fields, e.g., physics, mathematics, and
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2011.09128
We present a multigrid-in-channels (MGIC) approach that tackles the quadratic growth of the number of parameters with re
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
2011.10568
Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past kn
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Estimator Model for Prediction of Power Output of Wave Farms Using Machine Learning Methods
The amount of power generated by a wave farm depends on the Wave Energy Converter (WEC) arrangement along with the usual
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
NPAS: A Compiler-aware Framework of Unified Network Pruning and Architecture Search for Beyond Real-Time Mobile Acceleration
With the increasing demand to efficiently deploy DNNs on mobile edge devices, it becomes much more important to reduce u
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Quantum Dynamics of Optimization Problems
In this letter, by establishing the Schrödinger equation of the optimization problem, the optimization problem is transf
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Binding and Perspective Taking as Inference in a Generative Neural Network Model
The ability to flexibly bind features into coherent wholes from different perspectives is a hallmark of cognition and in
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Lagrangian Reachtubes: The Next Generation
We introduce LRT-NG, a set of techniques and an associated toolset that computes a reachtube (an over-approximation of t
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Weakly-Supervised Action Localization and Action Recognition using Global-Local Attention of 3D CNN
3D Convolutional Neural Network (3D CNN) captures spatial and temporal information on 3D data such as video sequences. H
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Evolutionary Variational Optimization of Generative Models
We combine two popular optimization approaches to derive learning algorithms for generative models: variational optimiza
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Computing Cliques and Cavities in Networks
Complex networks contain complete subgraphs such as nodes, edges, triangles, etc., referred to as simplices and cliques
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
A threshold search based memetic algorithm for the disjunctively constrained knapsack problem
The disjunctively constrained knapsack problem consists in packing a subset of pairwisely compatible items in a capacity
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
ES-ENAS: Efficient Evolutionary Optimization for Large Hybrid Search Spaces
In this paper, we approach the problem of optimizing blackbox functions over large hybrid search spaces consisting of bo
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Neuromorphic adaptive spiking CPG towards bio-inspired locomotion of legged robots
In recent years, locomotion mechanisms exhibited by vertebrate animals have been the inspiration for the improvement in
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Pseudo-Adaptive Penalization to Handle Constraints in Particle Swarm Optimizers
The penalization method is a popular technique to provide particle swarm optimizers with the ability to handle constrain
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Deep Evolutionary Learning for Molecular Design
In this paper, we propose a deep evolutionary learning (DEL) process that integrates fragment-based deep generative mode
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Evolutionary Multitask Optimization: a Methodological Overview, Challenges and Future Research Directions
In this work we consider multitasking in the context of solving multiple optimization problems simultaneously by conduct
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Learning How to Search: Generating Effective Test Cases Through Adaptive Fitness Function Selection
Search-based test generation is guided by feedback from one or more fitness functions - scoring functions that judge sol
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Towards Large Scale Automated Algorithm Design by Integrating Modular Benchmarking Frameworks
We present a first proof-of-concept use-case that demonstrates the efficiency of interfacing the algorithm framework Par
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
On the Post-hoc Explainability of Deep Echo State Networks for Time Series Forecasting, Image and Video Classification
Since their inception, learning techniques under the Reservoir Computing paradigm have shown a great modeling capability
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Combining Spiking Neural Network and Artificial Neural Network for Enhanced Image Classification
With the continued innovations of deep neural networks, spiking neural networks (SNNs) that more closely resemble biolog
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Neuroevolution of a Recurrent Neural Network for Spatial and Working Memory in a Simulated Robotic Environment
Animals ranging from rats to humans can demonstrate cognitive map capabilities. We evolved weights in a biologically pla
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
E$^2$CM: Early Exit via Class Means for Efficient Supervised and Unsupervised Learning
State-of-the-art neural networks with early exit mechanisms often need considerable amount of training and fine tuning t
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Pilot Investigation for a Comprehensive Taxonomy of Autonomous Entities
This paper documents an exploratory pilot study to define the term Autonomous Entity, and any characteristics that are r
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Endurance-Aware Mapping of Spiking Neural Networks to Neuromorphic Hardware
Neuromorphic computing systems are embracing memristors to implement high density and low power synaptic storage as cros
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Constrained plasticity reserve as a natural way to control frequency and weights in spiking neural networks
Biological neurons have adaptive nature and perform complex computations involving the filtering of redundant informatio
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Low Dimensional Landscape Hypothesis is True: DNNs can be Trained in Tiny Subspaces
Deep neural networks (DNNs) usually contain massive parameters, but there is redundancy such that it is guessed that the
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Hierarchical Program-Triggered Reinforcement Learning Agents For Automated Driving
Recent advances in Reinforcement Learning (RL) combined with Deep Learning (DL) have demonstrated impressive performance
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Shape-constrained Symbolic Regression -- Improving Extrapolation with Prior Knowledge
We investigate the addition of constraints on the function image and its derivatives for the incorporation of prior know
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
The Tangent Search Algorithm for Solving Optimization Problems
This article proposes a new population-based optimization algorithm called the Tangent Search Algorithm (TSA) to solve o
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
The World as a Graph: Improving El Niño Forecasts with Graph Neural Networks
Deep learning-based models have recently outperformed state-of-the-art seasonal forecasting models, such as for predicti
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
A Novel Generalised Meta-Heuristic Framework for Dynamic Capacitated Arc Routing Problems
The capacitated arc routing problem (CARP) is a challenging combinatorial optimisation problem abstracted from many real
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
A Rank based Adaptive Mutation in Genetic Algorithm
Traditionally Genetic Algorithm has been used for optimization of unimodal and multimodal functions. Earlier researchers
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Continuous Learning and Adaptation with Membrane Potential and Activation Threshold Homeostasis
Most classical (non-spiking) neural network models disregard internal neuron dynamics and treat neurons as simple input
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
SpikE: spike-based embeddings for multi-relational graph data
Despite the recent success of reconciling spike-based coding with the error backpropagation algorithm, spiking neural ne
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Universal scaling laws in the gradient descent training of neural networks
Current theoretical results on optimization trajectories of neural networks trained by gradient descent typically have t
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Covariance Matrix Adaptation Evolution Strategy Assisted by Principal Component Analysis
Over the past decades, more and more methods gain a giant development due to the development of technology. Evolutionary
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
HeunNet: Extending ResNet using Heun's Methods
There is an analogy between the ResNet (Residual Network) architecture for deep neural networks and an Euler solver for
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
PLSM: A Parallelized Liquid State Machine for Unintentional Action Detection
Reservoir Computing (RC) offers a viable option to deploy AI algorithms on low-end embedded system platforms. Liquid Sta
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
Optimal ANN-SNN Conversion for Fast and Accurate Inference in Deep Spiking Neural Networks
Spiking Neural Networks (SNNs), as bio-inspired energy-efficient neural networks, have attracted great attentions from r
Today in AI Intelligence
Loading technical market shifts and model velocity spikes...
TENSILE: A Tensor granularity dynamic GPU memory scheduling method toward multiple dynamic workloads system
Recently, deep learning has been an area of intense research. However, as a kind of computing-intensive task, deep learn