Search Results for author:
Found 13 papers, 4 papers with code
Adapting to time: why nature evolved a diverse set of neurons
Evolution has yielded a diverse set of neurons with varying morphologies and physiological properties that impact their processing of temporal information.
MindSet: Vision. A toolbox for testing DNNs on key psychological experiments
Multiple benchmarks have been developed to assess the alignment between deep neural networks (DNNs) and human vision.
Visual Reasoning in Object-Centric Deep Neural Networks: A Comparative Cognition Approach
To this end, these models use several kinds of attention mechanisms to segregate the individual objects in a scene from the background and from other objects.
The role of object-centric representations, guided attention, and external memory on generalizing visual relations
Visual reasoning is a long-term goal of vision research.
Successes and critical failures of neural networks in capturing human-like speech recognition
The constraints of the task, however, can nudge the cognitive science and engineering of audition to qualitatively converge, suggesting that a closer mutual examination would potentially enrich artificial hearing systems and process models of the mind and brain.
Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation
Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values.
Mixed Evidence for Gestalt Grouping in Deep Neural Networks
Here we test a total of 16 networks covering a variety of architectures and learning paradigms (convolutional, attention-based, supervised and self-supervised, feed-forward and recurrent) on dots (Experiment 1) and more complex shapes (Experiment 2) stimuli that produce strong Gestalts effects in humans.
Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be
When seeing a new object, humans can immediately recognize it across different retinal locations: the internal object representation is invariant to translation.
Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
Through the analysis of models' internal representations, we show that standard supervised CNNs trained on transformed objects can acquire strong invariances on novel classes even when trained with as few as 50 objects taken from 10 classes.
Generalisation in Neural Networks Does not Require Feature Overlap
That shared features between train and test data are required for generalisation in artificial neural networks has been a common assumption of both proponents and critics of these models.
The human visual system and CNNs can both support robust online translation tolerance following extreme displacements
Although translation is perhaps the simplest spatial transform that the visual system needs to cope with, the extent to which the human visual system can identify objects at previously unseen locations is unclear, with some studies reporting near complete invariance over 10{\deg} and other reporting zero invariance at 4{\deg} of visual angle.
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?
We find that the different measures provide different estimates of object selectivity, with precision and CCMAS measures providing misleadingly high estimates.
When and where do feed-forward neural networks learn localist representations?
We find that the number of local codes that emerge from a NN follows a well-defined distribution across the number of hidden layer neurons, with a peak determined by the size of input data, number of examples presented and the sparsity of input data.
