Bryan Tripp
YOU?
Author Swipe
View article: Deep networks for few-shot manipulation learning from scratch
Deep networks for few-shot manipulation learning from scratch Open
View article: FocalVid: A Platform for Tracking Visual Attention to Video via Crowdsourcing Validated Against Human Gaze Data
FocalVid: A Platform for Tracking Visual Attention to Video via Crowdsourcing Validated Against Human Gaze Data Open
Human attention to dynamic visual stimuli can be measured using mouse-contingent cursor movements as a proxy for tracking human gaze when eye tracking is not feasible, for example, in online studies. FocalVid is the first such platform for…
View article: Spatial organization of multisensory convergence in mouse isocortex
Spatial organization of multisensory convergence in mouse isocortex Open
1 Abstract The diverse functions of different cortical areas are thought to arise from their distinct groups of inputs. However, additional organizing principles may exist in the spatial structure of converging inputs. We investigated spat…
View article: Complex Properties of Training Stimuli Affect Brain Alignment in a Deep Network Model of Mouse Visual Cortex
Complex Properties of Training Stimuli Affect Brain Alignment in a Deep Network Model of Mouse Visual Cortex Open
Deep convolutional neural networks are important models of the visual cortex that ac-count relatively well for brain activity and are able to perform ethologically relevant functions. However, it is unknown which combination of factors, su…
View article: Multimodal Artificial Intelligence in Medicine
Multimodal Artificial Intelligence in Medicine Open
Traditional medical artificial intelligence models that are approved for clinical use restrict themselves to single-modal data ( e.g ., images only), limiting their applicability in the complex, multimodal environment of medical diagnosis …
View article: Utilization of Non-verbal Behaviour and Social Gaze in Classroom Human-Robot Interaction Communications
Utilization of Non-verbal Behaviour and Social Gaze in Classroom Human-Robot Interaction Communications Open
This abstract explores classroom Human-Robot Interaction (HRI) scenarios with an emphasis on the adaptation of human-inspired social gaze models in robot cognitive architecture to facilitate a more seamless social interaction. First, we de…
View article: Modeling the Role of Contour Integration in Visual Inference
Modeling the Role of Contour Integration in Visual Inference Open
Under difficult viewing conditions, the brain’s visual system uses a variety of recurrent modulatory mechanisms to augment feedforward processing. One resulting phenomenon is contour integration, which occurs in the primary visual (V1) cor…
View article: #3815 A DEEP LEARNING APPROACH TO PERSONALISED ANTI-HYPERTENSIVE MEDICATION TITRATION
#3815 A DEEP LEARNING APPROACH TO PERSONALISED ANTI-HYPERTENSIVE MEDICATION TITRATION Open
Background and Aims Hypertension is the number one risk factor for premature death worldwide. Artificial Intelligence (AI) Clinical Decision Support Systems are an important next step for hypertension management but require rigorous evalua…
View article: Modelling the role of contour integration in visual inference
Modelling the role of contour integration in visual inference Open
Under difficult viewing conditions, the brain’s visual system uses a variety of recurrent modulatory mechanisms to augment feed-forward processing. One resulting phenomenon is contour integration, which occurs in the primary visual (V1) co…
View article: MouseNet: A biologically constrained convolutional neural network model for the mouse visual cortex
MouseNet: A biologically constrained convolutional neural network model for the mouse visual cortex Open
Convolutional neural networks trained on object recognition derive inspiration from the neural architecture of the visual system in mammals, and have been used as models of the feedforward computation performed in the primate ventral strea…
View article: Spiking Approximations of the MaxPooling Operation in Deep SNNs
Spiking Approximations of the MaxPooling Operation in Deep SNNs Open
Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversi…
View article: CNN MouseNet: A biologically constrained convolutional neural network model for mouse visual cortex
CNN MouseNet: A biologically constrained convolutional neural network model for mouse visual cortex Open
Convolutional neural networks trained on object recognition derive inspiration from the neural architecture of the visual system in primates, and have been used as models of the feedforward computation performed in the primate ventral stre…
View article: Driving Scene Understanding: How much temporal context and spatial resolution is necessary?
Driving Scene Understanding: How much temporal context and spatial resolution is necessary? Open
Driving Scene Understanding is a broad field which addresses the problem of recognizing a variety of on-road situations; namely driver behaviour/intention recognition, driver-action causal reasoning, pedestriansâ and nearby vehiclesâ i…
View article: Investigating Therapies for Freezing of Gait Targeting the Cognitive, Limbic, and Sensorimotor Domains
Investigating Therapies for Freezing of Gait Targeting the Cognitive, Limbic, and Sensorimotor Domains Open
Background Freezing of gait (FOG) is arguably the most disabling motor symptom experienced with Parkinson’s disease (PD), but treatments are extremely limited due to our poor understanding of the underlying mechanisms. Three cortical domai…
View article: Comparison of Foveated Downsampling Techniques in Image Recognition
Comparison of Foveated Downsampling Techniques in Image Recognition Open
Foveation is an important part of human vision, and a number of deep networks have also used foveation. However, there have been few systematic comparisons between foveating and non-foveating deep networks, and between different variable…
View article: Neuron-based explanations of neural networks sacrifice completeness and interpretability
Neuron-based explanations of neural networks sacrifice completeness and interpretability Open
High quality explanations of neural networks (NNs) should exhibit two key properties. Completeness ensures that they accurately reflect a network's function and interpretability makes them understandable to humans. Many existing methods pr…
View article: Identifying and interpreting tuning dimensions in deep networks.
Identifying and interpreting tuning dimensions in deep networks. Open
In neuroscience, a dimension is a stimulus attribute that accounts for much of the activation variance of a group of neurons. These are commonly used to decipher the responses of such groups. While researchers have attempted to manually i…
View article: Inferring symbols from demonstrations to support vector-symbolic planning in a robotic assembly task
Inferring symbols from demonstrations to support vector-symbolic planning in a robotic assembly task Open
View article: A Convolutional Network Architecture Driven by Mouse Neuroanatomical Data
A Convolutional Network Architecture Driven by Mouse Neuroanatomical Data Open
Convolutional neural networks trained on object recognition derive some inspiration from the neuroscience of the visual system in primates, and have been used as models of the feedforward computation performed in the primate ventral stream…
View article: CRV 2020 Committees
CRV 2020 Committees Open
View article: Active Perception and Representation for Robotic Manipulation
Active Perception and Representation for Robotic Manipulation Open
The vast majority of visual animals actively control their eyes, heads, and/or bodies to direct their gaze toward different parts of their environment. In contrast, recent applications of reinforcement learning in robotic manipulation empl…
View article: How are response properties in the middle temporal area related to inference on visual motion patterns?
How are response properties in the middle temporal area related to inference on visual motion patterns? Open
View article: Approximating the Architecture of Visual Cortex in a Convolutional Network
Approximating the Architecture of Visual Cortex in a Convolutional Network Open
Deep convolutional neural networks (CNNs) have certain structural, mechanistic, representational, and functional parallels with primate visual cortex and also many differences. However, perhaps some of the differences can be reconciled. Th…
View article: A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations
A dataset of 40K naturalistic 6-degree-of-freedom robotic grasp demonstrations Open
Modern approaches to grasp planning often involve deep learning. However, there are only a few large datasets of labelled grasping examples on physical robots, and available datasets involve relatively simple planar grasps with two-fingere…
View article: Visually guided vergence in a new stereo camera system
Visually guided vergence in a new stereo camera system Open
People move their eyes several times each second, to selectivelyanalyze visual information from specific locations. This is impor-tant, because analyzing the whole scene in foveal detail would re-quire a beachball-sized brain and thousands…
View article: Guarding Against Adversarial Attacks using Biologically Inspired Contour Integration
Guarding Against Adversarial Attacks using Biologically Inspired Contour Integration Open
Artificial vision systems are susceptible to adversarial attacks. Smallintentional changes to images can cause these systems to mis-classify with high confidence. The brain has many mechanisms forstrengthening weak or confusing inputs. One…
View article: A video-driven model of response statistics in the primate middle temporal area
A video-driven model of response statistics in the primate middle temporal area Open
View article: Convolutional Neural Networks Regularized by Correlated Noise
Convolutional Neural Networks Regularized by Correlated Noise Open
Neurons in the visual cortex are correlated in their variability. The presence of correlation impacts cortical processing because noise cannot be averaged out over many neurons. In an effort to understand the functional purpose of correlat…
View article: Feature-Based Resource Allocation for Real-Time Stereo Disparity Estimation
Feature-Based Resource Allocation for Real-Time Stereo Disparity Estimation Open
The most accurate stereo disparity algorithms take dozens or hundreds of seconds to process a single frame. This timescale is impractical for many applications. However, high accuracy is often not needed throughout the scene. Here, we inve…
View article: Similarities and differences between stimulus tuning in the inferotemporal visual cortex and convolutional networks
Similarities and differences between stimulus tuning in the inferotemporal visual cortex and convolutional networks Open
Deep convolutional neural networks (CNNs) trained for object classification have a number of striking similarities with the primate ventral visual stream. In particular, activity in early, intermediate, and late layers is closely related t…