![](https://img-blog.csdnimg.cn/20201014180756930.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
phd
zjy2015302395
ACM要AC
展开
-
pytorch入门(3)
语言模型lstmimport torchtextfrom torchtext.vocab import Vectorsimport torchimport numpy as npimport randomBATCH_SIZE = 32EMBEDDING_SIZE = 100MAX_VOCAB_SIZE = 5000import torch.nn as nnclass RNNModel(nn.Module): def __init__(self, rnn_type,vocab_原创 2020-05-23 13:49:02 · 235 阅读 · 0 评论 -
pytorch入门(2)
fizzbuzz游戏3倍数fizz 5倍数buzz 15倍数fizzbuzz。其余数字输出本身12fizz4buzzfizz78fizzbuzz11fizz1314fizzbuzzdef fizz_buzz_encode(i): if i %15 == 0 : return 3 elif i%5 == 0 : return 2 elif i %3 == 0: return 1 else: return 0def fizz_buzz_de原创 2020-05-20 17:05:00 · 399 阅读 · 0 评论 -
pytorch入门(1)
import torchimport numpy as npN, D_in, H, D_out = 64,1000,100,10x = torch.randn(N,D_in)y = torch.randn(N,D_out)w1 = torch.randn(D_in, H,requires_grad = True)w2 = torch.randn(H,D_out,requires_grad = True)learning_rate = 1e-6for t in range(500):原创 2020-05-20 00:50:29 · 329 阅读 · 0 评论 -
Learning Local Search Heuristics for Boolean Satisfiability 2020-04-30
Learning Local Search Heuristics for Boolean SatisfiabilityAbstractGNN (select variable) + local search algorithm.RL,初始X,GNN结合sofetmax作为policy 函数,选择p最大的variable翻转,每个Trajectory有一个reward(找到使得fai为真的reward为1),训练参数。SAT problem: 属于[决定性问题],也是第一个被证明属于[NP完全]命原创 2020-05-17 03:26:00 · 561 阅读 · 0 评论 -
LEARNING A SAT SOLVER FROM SINGLE-BIT SUPERVISION 2020-05-01
LEARNING A SAT SOLVER FROM SINGLE-BIT SUPERVISIONAbstractNeuroSAT : a classifier to predict satisfiability of a propositional formulatrain NN ,2* LSTM+3* MLP (每个t : literal & variable 相互更新)监督学习, 二分类器。contribution:虽然结果一般,但是用监督学习的过程中,运用可视化发现,sat时可以发原创 2020-05-17 03:25:13 · 635 阅读 · 0 评论 -
NLocalSAT: Boosting Local Search with Solution Prediction 2020-05-02
NLocalSAT: Boosting Local Search with Solution PredictionAbstractNLocalSAT :address stochastic local search (SLS) 随机初始化的问题NLocalSAT combines SLS with a solution prediction model, which boosts SLS by changing initialization assignments with a neural net原创 2020-05-17 03:24:20 · 422 阅读 · 0 评论 -
Guiding High-Performance SAT Solvers with Unsat-Core Predictions 2020-05-03
Guiding High-Performance SAT Solvers with Unsat-Core PredictionsAbstractNeuroSAT is a method to improve CDCL solvers with predictions of unsat-cores.can provide effective guidance to high-performance SAT solvers on real problems.代码: https://github.com/原创 2020-05-17 03:23:27 · 362 阅读 · 0 评论 -
PDP: A General Neural Framework for Learning Constraint Satisfaction Solvers2020-05-04
PDP: A General Neural Framework for Learning Constraint Satisfaction SolversAbstractit is not clear how the search strategy in the learned models actually works. So propose a generic neural framework to solve CSP( constraint satisfaction problems) in a f原创 2020-05-17 03:22:36 · 336 阅读 · 0 评论 -
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search 2020-05-05
Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search图上常见np问题Abstractestimate the likelihood, for each vertex in a graph, of whether this vertex is part of the optimal solution.设计network 综合各种方案IntroductionGCN学习每个点的like原创 2020-05-17 03:21:42 · 1338 阅读 · 0 评论 -
Learning Combinatorial Optimization Algorithms over Graphs 2020-05-06
Learning Combinatorial Optimization Algorithms over GraphsAbstract解决NP-hard问题通常需要大量的专业知识和反复试验, learn algorithm to automate this challenging, tedious process. learn heuristic algorithm利用结构特征解决问题. (same structure but differ in the data)的性质,RL + graph embe原创 2020-05-17 03:20:24 · 2356 阅读 · 3 评论 -
NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT LEARNING 2020-05-07
NEURAL COMBINATORIAL OPTIMIZATION WITH REINFORCEMENT LEARNINGAbstract(借用pointer network用 policy gradient 优化,)given a set of city coordinates, predicts a distribution over different city permutations.RL(reward 总路径长度相反数) + RNN (policy gradient)很好的解决100no原创 2020-05-17 03:18:59 · 2123 阅读 · 0 评论 -
ATTENTION, LEARN TO SOLVE ROUTING PROBLEMS 2020-05-09
ATTENTION, LEARN TO SOLVE ROUTING PROBLEMSAbstract问题描述车辆路径问题(Vehicle Routing Problem, VRP), 车辆路线问题最早是由Dantzig和Ramser于1959年首次提出,它是指一定数量的客户,各自有不同数量的货物需求,配送中心向客户提供货物,由一个车队负责分送货物,组织适当的行车路线,目标是使得客户的需求得到满足,并能在一定的约束下,达到诸如路程最短、成本最小、耗费时间最少等目的。Daima:https://g原创 2020-05-17 03:18:16 · 909 阅读 · 0 评论 -
On Learning Combinatorial Patterns to Assist Large-Scale Airline Crew Pairing Optimization 2020-0...
On Learning Combinatorial Patterns to Assist Large-Scale Airline Crew Pairing OptimizationAbstractCPO :: 设计 legal flight sequence (crew pairings),以最低的成本设计出航空公司的航班时间表机组指派问题需要考虑时间变量以及后续的事件,比如a机组从北京飞到上海就只能飞上海的航班了,而且人家还必须回到北京,这个问题的复杂度就大多了。类似的还有登机口指派问题。机组排原创 2020-05-17 03:17:09 · 330 阅读 · 0 评论 -
Attention is all you need 2020-05-15
Attention is all you need AbstractTransformer : 无recurrence和convolutions,只基于attentionIntroductionRecurrent models 是seq2seq model,h_t = f (position,h_t-1);不能并行运算,RNN 长期忘记,transformer: averaging attention-weighted positionsSelf-attention : relating d原创 2020-05-17 03:14:05 · 201 阅读 · 0 评论