Results 21 to 30 of about 129,133 (91)

GitGraph - Architecture Search Space Creation through Frequent Computational Subgraph Mining [PDF]

open access: yesarXiv, 2018
The dramatic success of deep neural networks across multiple application areas often relies on experts painstakingly designing a network architecture specific to each task. To simplify this process and make it more accessible, an emerging research effort seeks to automate the design of neural network architectures, using e.g. evolutionary algorithms or
arxiv  

Social capital at venture capital firms and their financial performance: Evidence from China [PDF]

open access: yesarXiv, 2018
This paper studies the extent to which social capital drives performance in the Chinese venture capital market and explores the trend toward VC syndication in China. First, we propose a hybrid model based on syndicated social networks and the latent-variable model, which describes the social capital at venture capital firms and builds relationships ...
arxiv  

Financial Lie groups [PDF]

open access: yesarXiv, 2011
In this paper we see the evolution of a capitalized financial event e, with respect to a capitalization factor f, as the exponential map of a suitably defined Lie group G(f,e), supported by the half-space of capitalized financial events having the same capital sign of e.
arxiv  

Neural Networks for Portfolio-Level Risk Management: Portfolio Compression, Static Hedging, Counterparty Credit Risk Exposures and Impact on Capital Requirement [PDF]

open access: yesarXiv
In this paper, we present an artificial neural network framework for portfolio compression of a large portfolio of European options with varying maturities (target portfolio) by a significantly smaller portfolio of European options with shorter or same maturity (compressed portfolio), which also represents a self-replicating static hedge portfolio of ...
arxiv  

Towards Efficient SRAM-PIM Architecture Design by Exploiting Unstructured Bit-Level Sparsity [PDF]

open access: yesarXiv
Bit-level sparsity in neural network models harbors immense untapped potential. Eliminating redundant calculations of randomly distributed zero-bits significantly boosts computational efficiency. Yet, traditional digital SRAM-PIM architecture, limited by rigid crossbar architecture, struggles to effectively exploit this unstructured sparsity.
arxiv  

GEM-CRAP: a fusion architecture for focal seizure detection. [PDF]

open access: yesJ Transl Med
Shi J   +10 more
europepmc   +1 more source

Transfer learning-enhanced CNN-GRU-attention model for knee joint torque prediction. [PDF]

open access: yesFront Bioeng Biotechnol
Xie H   +5 more
europepmc   +1 more source

Home - About - Disclaimer - Privacy