output
19932026
most citedThe electronic thermal conductivity of graphene

229 citations

Showing 2018Show all

8 papers · 1 filter

cs.SD2018★ 28 cited

FloWaveNet : A Generative Flow for Raw Audio

Sungwon Kim, Sang-gil Lee, Jongyoon Song +2

Most modern text-to-speech architectures use a WaveNet vocoder for synthesizing high-fidelity waveform audio, but there have been limitations, such as high inference time, in its p…

cs.DC2018

Workload-aware Automatic Parallelization for Multi-GPU DNN Training

Sungho Shin, Youngmin Jo, Jungwook Choi +3

Deep neural networks (DNNs) have emerged as successful solutions for variety of artificial intelligence applications, but their very large and deep models impose high computational…

cs.LG2018★ 1 cited

SARN: Relational Reasoning through Sequential Attention

Jinwon An, Sungwon Lyu, Sungzoon Cho

This paper proposes an attention module augmented relational network called SARN(Sequential Attention Relational Network) that can carry out relational reasoning by extracting refe…

math.CO2018★ 1 cited

On chordal phylogeny graphs

Soogang Eoh, Suh-Ryung Kim

An acyclic digraph each vertex of which has indegree at most and outdegree at most is called an digraph for some positive integers and . Lee {\it et al.} (2…

math.CO2018

A graph with the partial order competition dimension greater than five

Jihoon Choi, Soogang Eoh, Suh-Ryung Kim

In this paper, we use the Erdös-Szekeres lemma to show that there exists a graph with partial order competition dimension greater than five.

nucl-ex2018★ 6 cited

"", a -Meson Nuclear Bound State, Observed in Reactions

PARC E15 collaboration, S. Ajimura, H. Asano +67

We observed a distinct peak in the invariant mass spectrum of , well below the mass threshold of . By selecting a relatively large mome…

cs.LG2018★ 1 cited

Energy-Efficient Inference Accelerator for Memory-Augmented Neural Networks on an FPGA

Seongsik Park, Jaehee Jang, Seijoon Kim +1

Memory-augmented neural networks (MANNs) are designed for question-answering tasks. It is difficult to run a MANN effectively on accelerators designed for other neural networks (NN…

cs.NE2018

Number Sequence Prediction Problems for Evaluating Computational Powers of Neural Networks

Hyoungwook Nam, Segwang Kim, Kyomin Jung

Inspired by number series tests to measure human intelligence, we suggest number sequence prediction tasks to assess neural network models' computational powers for solving algorit…