20 results for “receptive fields”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
This paper investigates the computational advantage of structured receptive fields in recurrent neural networks.
This paper argues for the importance of modularity and heterogeneity in AI architectures, contrasting the Transformer model with the structure of the cortex.
This paper investigates the use of contrastive objectives for brain decoding using functional MRI (fMRI) activity and shows that linear contrastive decoders outperform other methods.
This paper explores the role of noise in neural computation and its potential to regulate network participation.
While backpropagated gradients can predict human brain activity in the visual cortex, their spatial and temporal organization fundamentally diverges from the expected patterns of a biologically plausi…
This paper proposes a hybrid ANN-SNN pipeline that leverages pretrained ANNs to enable high-performance SNNs.
The paper demonstrates that quadratic integrate-and-fire (QIF) neurons are superior to leaky integrate-and-fire (LIF) neurons for gradient descent training in spiking neural networks because their con…
This paper addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception system…
Timing Yang, Predrag Neskovic, Jansen Seheult, Wenchao Han +3 more
This paper proposes a self-supervised visual model called RATS that discovers compositional structure in images.
This paper investigates whether deep learning models retain the phase/sign asymmetry of natural images in their hidden layers and tests it causally.
The paper studies the dynamics of completion in recursive models on hard Sudoku puzzles and identifies a common dynamical signature of completion across two recurrent architectures.
This paper introduces Neural Expansion, a framework that explains deep neural network generalization through the expansion of directionally-selective ray coverage in the input space.
Wajeeha Tahir, Anna Tegon, Lionnus Kesting, Gamze İslamoğlu +3 more
This paper introduces Spatial-TRM, a compact recursive model that improves spatial context prediction in natural images.
This paper investigates deep learning from a physics-informed perspective, examining its key features and surprises.
Maksym Zubkov, Carol Wu, Shiwei Yang, Param Mody +1 more
This paper studies the expressivity of shallow polynomial neural networks with monomial activation functions over finite fields, quantifying it by the cardinality of the neuromanifold and deriving low…
Zanyi Wang, Xin Lin, Haodong Li, Dengyang Jiang +2 more
This paper proposes ReChannel, a method for dense prediction using a pretrained DiT model, which keeps the encoder but removes the decoder and adapts it with task LoRA. ReChannel maps each token to it…