-
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∗. -
Leapfrogging for parallelism in deep neural networks
The dataset used in the paper is a neural network with L layers numbered 1,..., L, in which each of the hidden layers has N neurons. -
NITI: INTEGER TRAINING
The dataset used in this paper is MNIST, CIFAR10, and ImageNet. -
Training Over-Parameterized Deep Neural Networks
The dataset used in this paper is a collection of training data for over-parameterized deep neural networks. -
Neural Network Training on In-memory-computing Hardware with Radix-4 Gradients
The dataset used in this paper is a neural network training dataset with radix-4 gradients. -
Norm-based Generalization Bounds for Compositionally Sparse Neural Networks
The dataset used in this paper is a multilayered sparse neural network, specifically a convolutional neural network. -
Hybrid ELB-NN for accuracy and computational complexity tradeoffs
Hybrid ELB-NN for accuracy and computational complexity tradeoffs. Our experimental results indicate that the accuracy varies with the precisions of weights and activations with... -
A Mathematical Motivation for Complex-valued Convolutional Networks
A complex-valued convolutional network (convnet) implements the repeated application of the following composition of three operations, recursively applying the composition to an... -
TensorQuant
TensorQuant toolbox is used to apply fixed point quantization to DNNs. The simulations are focused on popular CNN topologies, such as Inception V1, Inception V3, ResNet 50 and... -
TransparentFPGAAccelerationwithTensorFlow
The dataset used in this paper is a collection of neural network acceleration with TensorFlow and FPGA. -
MIXED PRECISION TRAINING
The dataset used for training deep neural networks using half-precision floating point numbers. -
Depth Separation with Intra-layer Links
The dataset used in the paper is a collection of functions that can be represented by a deep network, but cannot be represented by a shallow network. -
Anomalous diffusion dynamics of learning in deep neural networks
The dataset used in the paper is not explicitly described, but it is mentioned that the authors used ResNet-14, ResNet-20, ResNet-56, and ResNet-110 networks, as well as... -
Transformations between deep neural networks
The dataset used in the paper is a collection of neural networks trained on different tasks, including scalar functions, two-dimensional vector fields, and images of a rotating... -
PANGAEA search space
A dataset of 425,896 unique activation functions, created using the PANGAEA search space. -
Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT
Three benchmark datasets: Act-Bench-CNN, Act-Bench-ResNet, and Act-Bench-ViT, created by training convolutional, residual, and vision transformer architectures from scratch with... -
Progressive Feedforward Collapse of ResNet Training
The dataset used in the paper is a ResNet trained on various datasets, including MNIST, Fashion MNIST, CIFAR10, STL10, and CIFAR100. -
ImageNet and Wiki103
The dataset used in the paper is ImageNet and Wiki103.
