User profiles for D. L. Yamins
 | Daniel YaminsAssistant Professor of Computer Science and Psychology, Stanford University Verified email at stanford.edu Cited by 14202 |
Pruning neural networks without any data by iteratively conserving synaptic flow
Pruning the parameters of deep neural networks has generated intense interest due to potential
savings in time, memory and energy both during training and at test time. Recent works …
savings in time, memory and energy both during training and at test time. Recent works …
Flexible neural representation for physics prediction
Humans have a remarkable capacity to understand the physical dynamics of objects in their
environment, flexibly capturing complex structures and interactions at multiple levels of …
environment, flexibly capturing complex structures and interactions at multiple levels of …
Brain-like object recognition with high-performing shallow recurrent ANNs
Deep convolutional artificial neural networks (ANNs) are the leading class of candidate
models of the mechanisms of visual processing in the primate ventral stream. While initially …
models of the mechanisms of visual processing in the primate ventral stream. While initially …
Hierarchical modular optimization of convolutional networks achieves representations similar to macaque IT and human ventral stream
Humans recognize visually-presented objects rapidly and accurately. To understand this
ability, we seek to construct models of the ventral stream, the series of cortical areas thought to …
ability, we seek to construct models of the ventral stream, the series of cortical areas thought to …
Task-driven convolutional recurrent models of the visual system
Feed-forward convolutional neural networks (CNNs) are currently state-of-the-art for object
classification tasks such as ImageNet. Further, they are quantitatively accurate models of …
classification tasks such as ImageNet. Further, they are quantitatively accurate models of …
Learning to play with intrinsically-motivated, self-aware agents
…, S Wang, LF Fei-Fei, DL Yamins - Advances in neural …, 2018 - proceedings.neurips.cc
Infants are experts at playing, with an amazing ability to generate novel structured
behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to …
behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to …
Learning physical graph representations from visual scenes
Convolutional Neural Networks (CNNs) have proved exceptional at learning representations
for visual object categorization. However, CNNs do not explicitly encode objects, parts, and …
for visual object categorization. However, CNNs do not explicitly encode objects, parts, and …
Identifying learning rules from neural network observables
The brain modifies its synaptic strengths during learning in order to better adapt to its
environment. However, the underlying plasticity rules that govern learning are unknown. Many …
environment. However, the underlying plasticity rules that govern learning are unknown. Many …
Toward goal-driven neural network models for the rodent whisker-trigeminal system
…, MJ Hartmann, DL Yamins - Advances in Neural …, 2017 - proceedings.neurips.cc
… Yamins Departments of Psychology and Computer Science Stanford Neurosciences Institute
Stanford University Stanford, CA 94305 yamins… Ha Hong, Daniel LK Yamins, Nicolas Pinto, …
Stanford University Stanford, CA 94305 yamins… Ha Hong, Daniel LK Yamins, Nicolas Pinto, …
Unsupervised neural network models of the ventral visual stream
… software installed, you can download article citation data to the citation manager of your
choice. Simply select your manager software from the list below and click Download. …
choice. Simply select your manager software from the list below and click Download. …