Questions tagged [optimization]

For questions about implementing and improving optimization algorithms used in creating AI programs, or optimization in general.

118 questions
过滤
排序
Tagged with
0
投票s
1answer
47次点击

我如何可以模拟通过选择具有增强学习的路由提供资产这个问题?

I would like to build a model based on reinforcement learning (RL) for the following scenario Recommend the best route (of cities listed for a given country) that satisfies the required criteria (...
0
投票s
1answer
22 views

Can a machine learning approach solve this constrained optimisation problem?

我曾与不同的分类,回归做和值的预测方法的聚类,等等。我想知道是否有基于整体分布的机器学习方法...
1
投票
0answers
39次

What is the difference between simulated annealing and deterministic annealing?

Not sure if this is the right place, but I was wondering if someone could briefly explain to me the differences & similarities between simulated annealing and deterministic annealing? I know that ...
1
投票
0answers
25 views

有多少训练运行都需要获得性能可靠的价值?

我试图优化神经网络。对于这一点,我改变了像批量大小,学习率,权重初始化等。参数神经网络是不确定性的算法,因此,在...
2
投票s
0answers
39次

如何逃脱新元局部极小?

SGD is able to jump out of local minima that would otherwise trap BGD I don't really understand the above statement. Could someone please provide a mathematical explanation for why SGD (Stochastic ...
1
投票
0answers
27 views

Which one is more important in case of different loss optimization algorithms, Speed or the Route?

我们有各种不同的算法来优化像AdaGrad,SGD +动量等损失有些人比其他人更常用。在一些算法,它们通常范围了他们之前...
0
投票s
0answers
29次

Simplifying Log Loss

I am reading through a paper (https://www.mitpressjournals.org/doi/pdf/10.1162/0891201053630273) where they describe logloss as a ranking function and can be simplified to the margin of the training ...
0
投票s
0answers
15次

这两个策略是最好的选择模拟退火的解决方案?

我使用模拟退火(SA)为NP-hard组合优化问题。1)我测试过的一系列问题的实例,其目标值可以在100级的或的...
0
投票s
0answers
12 views

What are swarm optimization techniques used for: training the ANN by weight optimization or for feature selection?

群智能(SI)是分散的,自组织系统,自然或人工的集体行为。这个概念被用在人工智能工作。betway电竞基于SI的算法,...
0
投票s
0answers
23次

Can neural networks handle redundant inputs?

I have a fully connected neural network with the following number of neurons in each layer[4,20,20,20,...,1]。我使用TensorFlow和4实值...
1
投票
3answers
87点意见

How to improve neural network training against a large data set of points with varying magnitude

我目前使用TensorFlow和都被简单地尝试直接训练神经网络对大量连续的数据集,例如$ Y = [0.014,1.545,10.232,0.948,...] $对应于...
1
投票
1answer
28点意见

什么是凸优化的AI系统中的作用?

Convex optimisation is defined as: I have seen a lot of talk about convex loss functions in Neural Networks and how we are optimising rewards or penalty in AI/ML systems. But I have never seen any ...
2
投票s
2answers
42次

How can I train a neural network if I don't have enough data?

I have created a neural network that is able to recognize images with the numbers 1-5. The issue is that I have a database of 16x5 images which ,unfortunately, is not proving enough as the neural ...
2
投票s
1answer
103次

其中深强化学习算法是适合我的问题吗?

My task is to solve an optimization problem with deep reinforcement learning. I read about several algorithms like DQN, PPO, DDPG, and A2C/A3C but use cases always seem to be problems like video games ...
4
投票s
1answer
53次

没有一批规范对梯度什么样的影响?

Batch norm is a technique where they essentially standardize the activations at each layer, before passing it on to the next layer. Naturally, this will affect the gradient through the network. I have ...

15 三十 50 每页
1
2 3 4 5
8