37 citations · 73 across the 14 of their papers we have counts for
15 papers
Studies with impossible languages falsify LMs as models of human language
Jeffrey S. Bowers, Jeff Mitchell
According to Futrell and Mahowald [arXiv:2501.17047], both infants and language models (LMs) find attested languages easier to learn than impossible languages that have unnatural s…
The role of object-centric representations, guided attention, and external memory on generalizing visual relations
Guillermo Puebla, Jeffrey S. Bowers
Visual reasoning is a long-term goal of vision research. In the last decade, several works have attempted to apply deep neural networks (DNNs) to the task of learning visual relati…
Convolutional Neural Networks Trained to Identify Words Provide a Surprisingly Good Account of Visual Form Priming Effects
Dong Yin, Valerio Biscione, Jeffrey Bowers
A wide variety of orthographic coding schemes and models of visual word identification have been developed to account for masked priming data that provide a measure of orthographic…
Successes and critical failures of neural networks in capturing human-like speech recognition
Federico Adolfi, Jeffrey S. Bowers, David Poeppel
Natural and artificial audition can in principle acquire different solutions to a given problem. The constraints of the task, however, can nudge the cognitive science and engineeri…
Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation
Milton L. Montero, Jeffrey S. Bowers, Rui Ponte Costa +2
Recent research has shown that generative models with highly disentangled representations fail to generalise to unseen combination of generative factor values. These findings contr…
Mixed Evidence for Gestalt Grouping in Deep Neural Networks
Valerio Biscione, Jeffrey S. Bowers
Gestalt psychologists have identified a range of conditions in which humans organize elements of a scene into a group or whole, and perceptual grouping principles play an essential…
Convolutional Neural Networks Are Not Invariant to Translation, but They Can Learn to Be
Valerio Biscione, Jeffrey S. Bowers
When seeing a new object, humans can immediately recognize it across different retinal locations: the internal object representation is invariant to translation. It is commonly bel…
Learning Online Visual Invariances for Novel Objects via Supervised and Self-Supervised Training
Valerio Biscione, Jeffrey S. Bowers
Humans can identify objects following various spatial transformations such as scale and viewpoint. This extends to novel objects, after a single presentation at a single pose, some…
Generalisation in Neural Networks Does not Require Feature Overlap
Jeff Mitchell, Jeffrey S. Bowers
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…
A case for robust translation tolerance in humans and CNNs. A commentary on Han et al
Ryan Blything, Valerio Biscione, Jeffrey Bowers
Han et al. (2020) reported a behavioral experiment that assessed the extent to which the human visual system can identify novel images at unseen retinal locations (what the authors…
Learning Translation Invariance in CNNs
Valerio Biscione, Jeffrey Bowers
When seeing a new object, humans can immediately recognize it across different retinal locations: we say that the internal object representation is invariant to translation. It is…
The human visual system and CNNs can both support robust online translation tolerance following extreme displacements
Ryan Blything, Valerio Biscione, Ivan I. Vankov +2
Visual translation tolerance refers to our capacity to recognize objects over a wide range of different retinal locations. Although translation is perhaps the simplest spatial tran…
Are there any 'object detectors' in the hidden layers of CNNs trained to identify objects or scenes?
Ella M. Gale, Nicholas Martin, Ryan Blything +2
Various methods of measuring unit selectivity have been developed with the aim of better understanding how neural networks work. But the different measures provide divergent estima…
Training neural networks to encode symbols enables combinatorial generalization
Ivan Vankov, Jeffrey Bowers
Combinatorial generalization - the ability to understand and produce novel combinations of already familiar elements - is considered to be a core capacity of the human mind and a m…
When and where do feed-forward neural networks learn localist representations?
Ella M. Gale, Nicolas Martin, Jeffrey S. Bowers
According to parallel distributed processing (PDP) theory in psychology, neural networks (NN) learn distributed rather than interpretable localist representations. This view has be…