23 papers · ranked by Valyu relevance
Eric Peh, Paritosh Parmar, Basura Fernando
We introduce the novel concept of visually Connecting Actions and Their Effects (CATE) in video understanding. CATE can have applications in areas like task planning and learning from demonstration. We identify and explore two different aspects of the concept of CATE: Action Selection (AS) and Effect-Affinity…
Olivier Codol, Paul L. Gribble, Kevin N. Gurney
The problem of selecting one action from a set of different possible actions, simply referred to as the problem of action selection, is a ubiquitous challenge in the animal world. For vertebrates, the basal ganglia (BG) are widely thought to implement the core computation to solve this problem, as the anatomy and…
Weng, Yueyang, Xiaopeng Zhang, Yongjin Mu + 4 more
— Action chunking is a widely adopted approach in Learning from Demonstration (LfD). By modeling multistep action chunks rather than single-step actions, action chunking significantly enhances modeling capabilities for human expert policies. However, the reduced decision frequency restricts the utilization of recent…
Wenbo Zhang, Hengrui Cai
Deep reinforcement learning (RL) has gained widespread adoption in recent years but faces significant challenges, particularly in unknown and complex environments. Among these, high-dimensional action selection stands out as a critical problem. Existing works often require a sophisticated prior design to eliminate…
Vincenzo G. Fiore, Raymond J. Dolan, Nicholas J. Strausfeld, Frank Hirth
'Frank Hirth'] Survival and reproduction entail the selection of adaptive behavioural repertoires. This selection manifests as phylogenetically acquired activities that depend on evolved nervous system circuitries. Lorenz and Tinbergen already postulated that heritable behaviours and their reliable performance are…
Hao Li, Xin Jin
The basal ganglia are known to be essential for action selection. However, the functional role of basal ganglia direct and indirect pathways in action selection remains unresolved. Here by employing cell-type-specific neuronal recording and manipulation in mice trained in a choice task, we demonstrate that multiple…
Hao Li, Xin Jin, Laura A Bradfield, Kate M Wassum
The basal ganglia are known to be essential for action selection. However, the functional role of basal ganglia direct and indirect pathways in action selection remains unresolved. Here, by employing cell-type-specific neuronal recording and manipulation in mice trained in a choice task, we demonstrate that multiple…
W. F. Mader, Satya Krishna Gorti, Maksims Volkovs, Guangwei Yu
k aggregation over the instance class activation sequence to generate video probabilities. Localization is then done by leveraging the class activation sequence to generate start and end predictions. However, in many cases, the instances that are selected in the top-k contain useful information for prediction but not…
David A. Rosenbaum, Kate M. Chapman, Chase J. Coelho, Lanyun Gong + 1 more
'Breanna E. Studenka'] Actions that are chosen have properties that distinguish them from actions that are not. Of the nearly infinite possible actions that can achieve any given task, many of the unchosen actions are irrelevant, incorrect, or inappropriate. Others are relevant, correct, or appropriate but are…
Vassilios Christopoulos, James Bonaiuto, Richard A. Andersen, Konrad Körding
'Konrad Körding'] Decision making is a vital component of human and animal behavior that involves selecting between alternative options and generating actions to implement the choices. Although decisions can be as simple as choosing a goal and then pursuing it, humans and animals usually have to make decisions in…
Sanghyun Yi, John P. O’Doherty
When encountering a novel situation, an intelligent agent needs to find out which actions are most beneficial for interacting with that environment. One purported mechanism for narrowing down the scope of possible actions is the concept of action affordance. Here, we delve into the neuro-computational mechanisms…
Shan Zhong, Nader Pouratian, Paul Schrater, Vassilios Christopoulos
Action selection in cluttered environments, where individuals must simultaneously pursue goals and avoid obstacles, presents a significant challenge for the brain. To understand the underlying mechanisms of action selection in such contexts, we propose a computational model that extends stochastic optimal control…
Jill Campbell Stewart, Kaci Handlery, Jessica F. Baird, Erika L. Blanck + 2 more
'Erika L. Blanck' 'Geetanjali Pathak' 'Stacy L. Fritz'] Action selection (AS), or selection of an action from a set of alternatives, is an important movement preparation process that engages a frontal-parietal network. The addition of AS demands to arm training after stroke could be used to engage this motor planning…
Shan Zhong, Nader Pouratian, Vassilios Christopoulos, Jason A Papin
Survival of species in an ever-changing environment requires a flexibility that extends beyond merely selecting the most appropriate actions. It also involves readiness to stop or switch actions in response to environmental changes. Although considerable research has been devoted to understanding how the brain switches…
Caroline Quoilin, Fanny Fievez, Julie Duque
By applying transcranial magnetic stimulation (TMS) over the primary motor cortex (M1) to elicit motor-evoked potentials (MEPs) in muscles of the contralateral hand during reaction time (RT) tasks, many studies have reported a strong suppression of MEPs during action preparation, a phenomenon called preparatory…
Indrė Žliobaitė, Mykola Pechenizkiy
Different machine learning techniques have been proposed and used for modeling individual and group user needs, interests and preferences. In the traditional predictive modeling instances are described by observable variables, called attributes. The goal is to learn a model for predicting the target variable for unseen…
Elena Zamaraeva, Christopher M. Collins, Dmytro Antypov, Vladimir V. Gusev + 6 more
Crystal Structure Prediction (CSP) is a fundamental computational problem in materials science. Basin-hopping is a prominent CSP method that combines global Monte Carlo sampling to search over candidate trial structures with local energy minimisation of these candidates. The sampling uses a stochastic policy to…
Andrei Nica, Khimya Khetarpal, Doina Precup
Decision-making AI agents are often faced with two important challenges: the depth of the planning horizon, and the branching factor due to having many choices. Hierarchical reinforcement learning methods aim to solve the first problem, by providing shortcuts that skip over multiple time steps. To cope with the…
Umakant Mishra
| 1. Introduction 1 | | --- | | 2. Inventions on selecting GUI elements 3 | | 2.1 Time-space object containment for graphical user interface 3 | | 2.2 Method and apparatus for selecting and displaying items in a notebook | | graphical user interface 4 | | 2.3 Refresh and select-all actions in graphical user interface 5…
Katrina R. Quinn, Florian Sandhaeger, Nima Noury, Ema Žeželić + 1 more
Perceptual decisions have long been framed in terms of the actions used to report a choice. Accordingly, studies of perceptual decision-making have historically relied on tasks with fixed choice-response mappings, in which choice and motor response are inextricably linked. Although several studies have since…
Elisabeth Rounis, Zuo Zhang, Gloria Pizzamiglio, Mihaela Duta + 1 more
'Glyn Humphreys'] We assessed the factors influencing the planning of actions required to manipulate one of two everyday objects with matching dimensions but openings at opposite ends: a cup and a vase. We found that, for cups, measures of movement preparation to reach and grasp the object were influenced by whether…
Authors not listed
The identification of kinetically feasible reaction pathways that connect a reactant to its product, including numerous intermediates and transition states, is crucial for predicting chemical reactions and elucidating reaction mechanisms. However, as molecular systems become increasingly complex or larger, the number…
Authors not listed
While virtual libraries of synthetically accessible compounds have exploded in size to many billions, our capacity to extract valuable drug leads from these vast databases remains limited by computational resources. To overcome this, we developed SLICE SMARTS and Logic In ChEmistry), a powerful new tool designed for…