-
A Logical Calculus of the Ideas Immanent in Nervous Activity
The dataset used in the paper is related to neural networks and artificial intelligence. -
Energy-based out-of-distribution detection
Energy-based out-of-distribution detection. -
Enhancing the reliability of out-of-distribution image detection in neural ne...
Enhancing the reliability of out-of-distribution image detection in neural networks. -
A baseline for detecting misclassified and out-of-distribution examples in ne...
A baseline for detecting misclassified and out-of-distribution examples in neural networks. -
MERCURY: Accelerating DNN Training By Exploiting Input Similarity
MERCURY accelerates DNN training by exploiting input similarity. -
Google Edge TPU
The dataset consists of 24 state-of-the-art Google edge neural network models, including CNNs, LSTMs, Transducers, and RCNNs. -
Pattern Formation in a Spiking Neural-Field of Renewal Neurons
The dataset used in this paper is a network of renewal neurons, a well-established class of spiking cells. The network's dynamics can be accurately represented by a partial... -
Non-random network connectivity comes in pairs
The dataset is used to analyze the occurrence of bidirectional connections in local cortical networks. -
Zenkai - Framework for Exploring Beyond Backpropagation
Zenkai is an open-source framework designed to give researchers more control and flexibility over building and training deep learning machines. -
Noisy Recurrent Neural Networks
The dataset is a class of noisy recurrent neural networks with w (unbounded) weights for classification of sequences of length T, where independent noise distributed according... -
Chaos in Homeostatically Regulated Neural Systems
The dataset used in the paper is a Wilson-Cowan network with homeostatic regulation, which is a model of neural activity. -
Learning a Single Neuron with Gradient Methods
We consider the fundamental problem of learning a single neuron x (cid:55)→ σ(w(cid:62)x) in a realizable setting, using standard gradient methods with random initialization,... -
MDENet: Multi-modal Dual-embedding Networks for Malware Open-set Recognition
Malware open-set recognition: the samples of only known families are presented during training, while the recognition system is expected to recognize samples from both known and... -
Liquid State Machine
The dataset used in this paper is a liquid state machine (LSM) with a liquid composed of LIF neurons. The liquid is a set of recurrent spiking neurons that are randomly... -
Topology-dependent coalescence controls power-law exponents in finite networks
The dataset used in the paper is a finite-size branching network model with various connectivity structures, ranging from spatially arranged networks to random or all-to-all... -
Synthetic dataset for Leaky ResNets
The dataset used in the paper is a synthetic dataset generated by teacher networks for a given true rank k∗. -
Discontinuous Neural Network for Non-Negative Sparse Approximation
The dataset is used to model the mammalian olfactory system and solve non-negative sparse approximation problems. -
Large scale Lasso with windowed active set for convolutional spike sorting
The dataset used in the paper is a large-scale spike sorting dataset, containing recordings from a population of neurons with up to 4000 electrodes, 1000 neurons, and 108 time...