A New Method for Mapping Optimization Problems Onto Neural Networks

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Practical Black-Box Attacks against Machine Learning (2016, methodology): “ kernel 2x2 [24], a convolutional layer of 64 kernels of size 2x2, a max pooling layer of kernel 2x2, two layers of 200 rectiﬁed linear units [18], and a softmax layer to produce a probability vector [23]. The architecture is trained for three substitute training epochs on our local machine3. We use”
Parallel Distributed Approaches to Combinatorial Optimization: Benchmark Studies on Traveling Salesman Problem (1990, methodology): “[3] a method for estimating Tc in advance by estimating the eigenvalue distibution of the linearized version of eq.”
Markov Random Field Modeling in Image Analysis (2001, methodology): “In (Peterson and Soderberg 1989), the convergence is judged by a quantity de ned as”
Portfolio selection using neural networks (2005, methodology): “For solving the portfolio optimisation problem, we have implemented a Hopfield network with gains b i changing through time [14].”