资源列表
RNN_matlab
- 用Matlab实现了最基本的RNN神经网络(Matlab to achieve the most basic RNN neural network)
is_pos_answer_intents_classifies
- 判断一句话是否定句还是肯定句,基于神经网络(pybrain)分类肯定句与否定句,开放了训练代码和样本数据,供读者自行修改样本进行训练(Is a sentence positive or negative?)
卷积层,池化层样例
- tensorflow框架下的卷积层,池化层说明与样例,代码(Convolution layer, pooling layer illustration and sample code)
循环神经网络
- tensorflow框架下的循环神经网络实例代码,前向传播方式(Recurrent neural network instance code under tensorflow framework, forward propagation mode)
seq2seq样例
- tensorflow框架下的交叉熵计算代码,序列到序列预测实例代码(Cross entropy calculation code, sequence to sequence prediction code)
bag2matlab-master
- ROS bag convert to mat
matconvnet-1.0-beta25
- matconvnet-25编译好的文件,确保放到matlab里面可以正常运行。(Matconvnet-25 compiled files to ensure that the Matlab can run normally.)
pytorch-a2c-ppo-acktr-master
- 改代码为ACKTR代码,该算法比传统的TRPO和DQN在运行速度和计算量都有很大的提升(scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation)
dbn-master
- 度信念网络是一个概率生成模型,与传统的判别模型的神经网络相对,生成模型是建立一个观察数据和标签之间的联合分布,对P(Observation|Label)和 P(Label|Observation)都做了评估,而判别模型仅仅而已评估了后者,也就是P(Label|Observation)。(The degree belief network is a probability generation model. Compared with the neural network of the tradi
DNN
- 深度神经网络搭建,搭建一个深层的神经网络用于训练。(A deep neural network is built to build a deep neural network for training.)
迁移学习对花进行分类
- 迁移学习简单算法,涉及到迁移学习的一些简单原理,学习参考使用(transfer_learning.py)
RBF_Plot
- 使用S函数进行编写RBF神经网络算法,并有画图分析程序。(Using S function to write RBF neural network algorithm, and drawing analysis program.)