Related papers: On the Minimal Set of Inputs Required for Efficien…
It is a central challenge in deep learning to understand how neural networks learn representations. A leading approach is the Neural Feature Ansatz (NFA) (Radhakrishnan et al. 2024), a conjectured mechanism for how feature learning occurs.…
Artificially evolving foraging behavior in simulated legged animals has proved to be a notoriously difficult task. Here, we co-evolve the morphology and controller for virtual organisms in a three-dimensional physically realistic…
A large challenge in Artificial Intelligence (AI) is training control agents that can properly adapt to variable environments. Environments in which the conditions change can cause issues for agents trying to operate in them. Building…
Combining a spatiotemporal, multi-agent based model of a foraging ecosystem with linear, genetically programmed rules for the agents' behaviors results in implicit, endogenous, objective functions and selection algorithms based on "natural…
Many foraging animals find food using composite random search strategies, which consist of intensive and extensive search modes. Models of composite search can generate predictions about how optimal foragers should behave in each search…
We investigate the matching of agents to resources in a computational ecology configured to present heterogeneous resource patches to evolving, neurally controlled agents. We repeatedly find a nearly optimal, ideal free distribution (IFD)…
Search processes in the natural world are often punctuated by home returns that reset the position of foraging animals, birds, and insects. Many theoretical, numerical, and experimental studies have now demonstrated that this strategy can…
Evolutionary deep intelligence synthesizes highly efficient deep neural networks architectures over successive generations. Inspired by the nature versus nurture debate, we propose a study to examine the role of external factors on the…
In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount…
Unmanned Aerial Vehicles (UAVs) have a great potential to support search tasks in unstructured environments. Small, lightweight, low speed and agile UAVs, such as multi-rotors platforms can incorporate many kinds of sensors that are…
Animals behave adaptively in the environment with multiply competing goals. Understanding of the mechanisms underlying such goal-directed behavior remains a challenge for neuroscience as well for adaptive system research. To address this…
Collective animal movement fascinates children and scientists alike. One of the most commonly given explanations for collective animal movement is improved foraging. Animals are hypothesized to gain from searching for food in groups. Here,…
Empowerment -- a domain independent, information-theoretic metric -- has previously been shown to assist in the evolutionary search for neural cellular automata (NCA) capable of homeostasis when employed as a fitness function. In our…
Flying insects are capable of vision-based navigation in cluttered environments, reliably avoiding obstacles through fast and agile maneuvers, while being very efficient in the processing of visual stimuli. Meanwhile, autonomous micro air…
Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks,…
We present a simple model to study L\'{e}vy-flight foraging in a finite landscape with countable targets. In our approach, foraging is a step-based exploratory random search process with a power-law step-size distribution $P(l) \propto…
How many of a neural network's parameters actually encode task-specific information? We investigate this question with LottaLoRA, a training paradigm in which every backbone weight is drawn at random and frozen; only low-rank LoRA adapters…
Few-shot learning aims to adapt knowledge learned from previous tasks to novel tasks with only a limited amount of labeled data. Research literature on few-shot learning exhibits great diversity, while different algorithms often excel at…
We present a suite of scalable algorithms for minimizing feedback arcs in large-scale weighted directed graphs, with the goal of revealing biologically meaningful feedforward structure in neural connectomes. Using the FlyWire Connectome…
Structural pruning has become an integral part of neural network optimization, used to achieve architectural configurations which can be deployed and run more efficiently on embedded devices. Previous results showed that pruning is possible…