-
Subregular Complexity and Deep Learning
The dataset consists of six formal target languages defined for training and testing purposes. Each language is a subset of the alphabet {a, b, c, d}. -
Membership-Invariant Subspace Training
Membership-Invariant Subspace Training (MIST) is a method for training classifiers that acts as a defense designed to specifically defend against black-box membership inference... -
Attacking Adversarial Attacks as A Defense
The dataset used in the paper is not explicitly described, but it is mentioned that the authors examined state-of-the-art attacks of various kinds. -
Fully Automatic Liver Attenuation Estimation combining CNN Segmentation and M...
The ALARM method is a fully automated liver attenuation estimation method that combines deep convolutional neural network (DCNN) and morphological operations. -
Improved Diagnosis of Tibiofemoral Cartilage Defects on MRI Images Using Deep...
MRI images of knee joint for cartilage defect diagnosis -
ProTuner: Tuning Programs with Monte Carlo Tree Search
The dataset used in the paper is a suite of 16 real benchmarks for deep learning and image processing applications. -
Computational cytometer based on magnetically modulated coherent imaging and ...
Computational cytometer based on magnetically modulated coherent imaging and deep learning -
Multi-Labelled Value Networks for Computer Go
A new approach to a value network architecture for the game Go, called a multi-labelled (ML) value network. The ML value network has the three advantages, offering different... -
CeBed: A Benchmark for Deep Data-Driven OFDM Channel Estimation
CeBed is a benchmark for deep data-driven OFDM channel estimation. -
Deep Claim: Payer Response Prediction from Claims Data with Deep Learning
Claims data from two US health systems with a general patient population and diverse payer mixes. -
Bandana: Using Non-volatile Memory for Storing Deep Learning Models
Typical large-scale recommender systems use deep learning models that are stored on a large amount of DRAM. These models often rely on embeddings, which consume most of the... -
Quality control stress test for deep learning-based diagnostic model in digit...
Quality control stress test for deep learning-based diagnostic model in digital pathology. -
MERCURY: Accelerating DNN Training By Exploiting Input Similarity
MERCURY accelerates DNN training by exploiting input similarity. -
ECG-CODE dataset
A dataset for ECG delineation and a self-trained method for improving the quality of fiducial points prediction within an ECG record. -
Channel Attention Networks for Robust MR Fingerprinting Matching
Magnetic Resonance Fingerprinting (MRF) dataset for tissue parameter estimation -
LoRa dataset
A LoRa dataset collected from 50 Pycom devices, and analyzed the performance of CNN-based RF fingerprinting on short- and long-term variations. -
WiFi 802.11b dataset
A large-scale WiFi 802.11b dataset, collected from 50 Pycom devices, and analyzed the performance of CNN-based RF fingerprinting on short- and long-term variations using LoRa... -
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. -
Energy Reconstruction from TAIGA-IACT Images using Deep Learning Methods
The dataset used for energy reconstruction in TAIGA-IACT images using deep learning methods.