Search Results for author:
Found 33 papers, 23 papers with code
Look Around! Unexpected gains from training on environments in the vicinity of the target
Here we present a new methodology to evaluate such generalization of RL agents under small shifts in the transition probabilities.
Sparse Distributed Memory is a Continual Learner
Continual learning is a problem for artificial neural networks that their biological counterparts are adept at solving.
BrainBERT: Self-supervised representation learning for intracranial recordings
We create a reusable Transformer, BrainBERT, for intracranial recordings bringing modern representation learning approaches to neuroscience.
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
"Forward-only" algorithms, which train neural networks while avoiding a backward pass, have recently gained attention as a way of solving the biologically unrealistic aspects of backpropagation.
Learning to Learn: How to Continuously Teach Humans and Machines
For example, when we learn mathematics at school, we build upon our knowledge of addition to learn multiplication.
Efficient Zero-shot Visual Search via Target and Context-aware Transformer
Target modulation is computed as patch-wise local relevance between the target and search images, whereas contextual modulation is applied in a global fashion.
Reason from Context with Self-supervised Learning
To better accommodate the object-centric nature of current downstream tasks such as object recognition and detection, various methods have been proposed to suppress contextual biases or disentangle objects from contexts.
Human or Machine? Turing Tests for Vision and Language
To address this question, we turn to the Turing test and systematically benchmark current AIs in their abilities to imitate humans.
Red Teaming with Mind Reading: White-Box Adversarial Policies Against RL Agents
In this work, we study white-box adversarial policies and show that having access to a target agent's internal state can be useful for identifying its vulnerabilities.
Improving generalization by mimicking the human visual diet
We present a new perspective on bridging the generalization gap between biological and computer vision -- mimicking the human visual diet.
Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass
Supervised learning in artificial neural networks typically relies on backpropagation, where the weights are updated based on the error-function gradients and sequentially propagated from the output layer to the input layer.
On the Efficacy of Co-Attention Transformer Layers in Visual Question Answering
In recent years, multi-modal transformers have shown significant progress in Vision-Language tasks, such as Visual Question Answering (VQA), outperforming previous architectures by a considerable margin.
Robust Feature-Level Adversaries are Interpretability Tools
We demonstrate that they can be used to produce targeted, universal, disguised, physically-realizable, and black-box attacks at the ImageNet scale.
Visual Search Asymmetry: Deep Nets and Humans Share Similar Inherent Biases
To elucidate the mechanisms responsible for asymmetry in visual search, we propose a computational model that takes a target and a search image as inputs and produces a sequence of eye movements until the target is found.
What can human minimal videos tell us about dynamic recognition models?
In human vision objects and their parts can be visually recognized from purely spatial or purely temporal information but the mechanisms integrating space and time are poorly understood.
Tuned Compositional Feature Replays for Efficient Stream Learning
To address the limited number of existing online stream learning datasets, we introduce 2 new benchmarks by adapting existing datasets for stream learning.
When Pigs Fly: Contextual Reasoning in Synthetic and Natural Scenes
Our model captures useful information for contextual reasoning, enabling human-level performance and better robustness in out-of-context conditions compared to baseline models across OCD and other out-of-context datasets.
Look Twice: A Generalist Computational Model Predicts Return Fixations across Tasks and Species
Primates constantly explore their surroundings via saccadic eye movements that bring different parts of an image into high resolution.
Fooling the primate brain with minimal, targeted image manipulation
Here we propose an array of methods for creating minimal, targeted image perturbations that lead to changes in both neuronal activity and perception as reflected in behavior.
What am I Searching for: Zero-shot Target Identity Inference in Visual Search
Using those error fixations, we developed a model (InferNet) to infer what the target was.
Can Deep Learning Recognize Subtle Human Activities?
Deep Learning has driven recent and exciting progress in computer vision, instilling the belief that these algorithms could solve any visual task.
Frivolous Units: Wider Networks Are Not Really That Wide
We identify two distinct types of "frivolous" units that proliferate when the network's width is increased: prunable units which can be dropped out of the network without significant change to the output and redundant units whose activities can be expressed as a linear combination of others.
Putting visual object recognition in context
To model the role of contextual information in visual recognition, we systematically investigated ten critical properties of where, when, and how context modulates recognition, including the amount of context, context and object resolution, geometrical structure of context, context congruence, and temporal dynamics of contextual modulation.
Variational Prototype Replays for Continual Learning
In each classification task, our method learns a set of variational prototypes with their means and variances, where embedding of the samples from the same class can be represented in a prototypical distribution and class-representative prototypes are separated apart.
Gradient-free activation maximization for identifying effective stimuli
To circumvent this problem, we developed a method for gradient-free activation maximization by combining a generative neural network with a genetic algorithm.
Lift-the-flap: what, where and when for context reasoning
Context reasoning is critical in a wide variety of applications where current inputs need to be interpreted in the light of previous experience and knowledge.
What am I Searching for: Zero-shot Target Identity Inference in Visual Search
Using those error fixations, we developed a model (InferNet) to infer what the target was.
A neural network trained to predict future video frames mimics critical properties of biological neuronal responses and perception
Interestingly, recent work has shown that deep convolutional neural networks (CNNs) trained on large-scale image recognition tasks can serve as strikingly good models for predicting the responses of neurons in visual cortex to visual stimuli, suggesting that analogies between artificial and biological neural networks may be more than superficial.
Learning Scene Gist with Convolutional Neural Networks to Improve Object Recognition
We use a biologically inspired two-part convolutional neural network ('GistNet') that models the fovea and periphery to provide a proof-of-principle demonstration that computational object recognition can significantly benefit from the gist of the scene as contextual information.
Recurrent computations for visual pattern completion
First, subjects robustly recognized objects even when rendered <15% visible, but recognition was largely impaired when processing was interrupted by backward masking.
On the Robustness of Convolutional Neural Networks to Internal Architecture and Weight Perturbations
We show that convolutional networks are surprisingly robust to a number of internal perturbations in the higher convolutional layers but the bottom convolutional layers are much more fragile.
Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning
Here, we explore prediction of future frames in a video sequence as an unsupervised learning rule for learning about the structure of the visual world.
Unsupervised Learning of Visual Structure using Predictive Generative Networks
The ability to predict future states of the environment is a central pillar of intelligence.
