基于CNNs的手写字符识别系统，载入MNIST手写字符数据库，通过训练提取特征，达到99 的识别率-Based on CNNs handwritten character recognition system, load MNIST handwritten character database, extract features through training, up to 99 recognition rate

lr.py是用python实现了逻辑回归的源代码，并附带有注释。mlp.py是用python实现了多层感知机的源代码，并附带有注释。LeNetConvPoolLayer.py是用python实现了LeNet网络，并附带有注释。该文件需要引用mlp.py。-lr.py is python source code achieving a logistic regression , along with comments. mlp.py realized MLP by python, along wi

医疗3d处理，即基于卷积神经网络的医疗影像分析平台(NiftyNet is a TensorFlow-based open-source convolutional neural networks (CNNs) platform for research in medical image analysis)

通过使用CNN来实现验证码识别的多任务学习(Using CAN to Achieve Multi-tasking Learning of Captcha Identification)