07 2020 档案
摘要：小跳最近在搭建一个数值仿真环境，由于需要用到python里面的一些库，所以不得不把simulink的模型搬过来，我们都知道在simulink里，仿真的时候设置仿真步长和微分方程求解器是必要的步骤。但是为什么要设置这个小跳却早已忘记了。一年级的时候搬砖搬多了，数分课也没好好上，回头一看，这么简单的东西，当时竟然整的稀里糊涂的。为什么要用RK4先po一张图，直观感受一下仿真的误差。对于给定线性常微分方...
阅读全文
摘要：gym调用gym的调用遵从以下的顺序env = gym.make('x')observation = env.reset()for i in range(time_steps):env.render()action = policy(observation)observation, reward, done, info = env.step(action)if done: …… bre...
阅读全文
摘要：MNIST 识别手写数字练习导入包、数据from keras.datasets import mnistimport matplotlib.pyplot as plt(X_train, Y_train),(X_test, Y_test) = mnist.load_data()from keras import Model, Input, metrics, optimizersfrom keras....
阅读全文
摘要：Trigger Word DetectionWelcome to the final programming assignment of this specialization! In this week's videos, you learned about applying deep learning to speech recognition. In this assignment, you...
阅读全文
摘要：Neural Machine TranslationWelcome to your first programming assignment for this week! You will build a Neural Machine Translation (NMT) model to translate human-readable dates ("25th of June, 2009") i...
阅读全文
摘要：Emojify!Welcome to the second assignment of Week 2. You are going to use word vector representations to build an Emojifier. Have you ever wanted to make your text messages more expressive? Your emojif...
阅读全文
摘要：Operations on word vectorsWelcome to your first assignment of this week! Because word embeddings are very computationally expensive to train, most ML practitioners will load a pre-trained set of embed...
阅读全文
摘要：Improvise a Jazz Solo with an LSTM NetworkWelcome to your final programming assignment of this week! In this notebook, you will implement a model that uses an LSTM to generate music. You will even be ...
阅读全文
摘要：Character level language model - Dinosaurus Island Welcome to Dinosaurus Island! 65 million years ago, dinosaurs existed, and in this assignment they
阅读全文
摘要：Building your Recurrent Neural Network - Step by StepWelcome to Course 5's first assignment! In this assignment, you will implement key components of a Recurrent Neural Network in numpy.Recurrent Neur...
阅读全文
摘要：概述：处理样本数不规则的模型recurrent neural network递归神经网络参数共享,前->后样本逐个扫描a激活用一套参数y激活用一套参数参数流x、y个数不一致的RNN序列样本分类问题音乐生成、机器翻译RNN类型总结language model with RNN输出P(sentence),并按照y(i)展开为字符串从训练模型采样在训练过程中，结局梯度爆炸gradient clippin...
阅读全文
摘要：Face RecognitionIn this assignment, you will build a face recognition system. Many of the ideas presented here are from FaceNet. In lecture, we also talked about DeepFace. Face recognition problems co...
阅读全文
摘要：Autonomous driving - Car detectionWelcome to your week 3 programming assignment. You will learn about object detection using the very powerful YOLO model. Many of the ideas in this notebook are descri...
阅读全文
摘要：Residual NetworksWelcome to the second assignment of this week! You will learn how to build very deep convolutional networks, using Residual Networks (ResNets). In theory, very deep networks can repre...
阅读全文
摘要：Keras tutorial - Emotion Detection in Images of FacesWelcome to the first assignment of week 2. In this assignment, you will:Learn to use Keras, a high-level neural networks API (programming framework...
阅读全文
摘要：Convolutional Neural Networks: ApplicationWelcome to Course 4's second assignment! In this notebook, you will:Implement helper functions that you will use when implementing a TensorFlow modelImplement...
阅读全文
摘要：根据国际系统工程协会（INCOSE）在 2007 年发布的《SE 愿景 2020》中的定义，MBSE 是建模方法在系统工程中的形式化应用，用以支持在系统全生命周期内开展需求、设计、分析、验证和确认相关的活动。从定义可以看到，MBSE 是基于文档的传统系统工程工作模式的演进，力求以多视角的系统模型做为桥梁，将跨学科/领域的模型关联起来，实现跨学科/领域的模型追溯，从而驱动大型复杂系统生存周期内各阶段...
阅读全文
摘要：Convolutional Neural Networks: Step by StepWelcome to Course 4's first assignment! In this assignment, you will implement convolutional (CONV) and pooling (POOL) layers in numpy, including both forwar...
阅读全文
摘要：本文转自知乎（Sophia）公众号【计算机视觉联盟】笔记图片由 TessFerrandez 整理，这套信息图优美地记录了深度学习课程的知识与亮点。因此它不仅仅适合初学者了解深度学习，还适合机器学习从业者和研究者复习基本概念。这不仅仅是一份课程笔记，同时还是一套信息图与备忘录。从深度学习基础、卷积网络和循环网络三个方面介绍该笔记1. 深度学习基本概念监督学习：所有输入数据都有确定的对应输出数据，在各...
阅读全文
摘要：Welcome to this week's programming assignment. Until now, you've always used numpy to build neural networks. Now we will step you through a deep learning framework that will allow you to build neural networks more easily.
阅读全文
摘要：Texpad live 编辑模式，即时编译 缺点：不支持高级packages，如cref 所以最后加 \crefname{figure}{Fig.}{Figs.} \crefname{table}{Table.}{Tables.} \crefname{appendix}{}{} \crefname{
阅读全文
摘要：人工智能：机器学习AI分类图分类几种网络结构分类NN——回归预测CNN（convolution NN）卷积神经网络——图片RNN (Recurrent Neural Network）递归神经网络——声音、语言处理LSTM长短期记忆网络——激活函数sigmoidReLU——rectified linear unit 修正线性单元概念Cost function 每个样本的误差均值Loss functi...
阅读全文
浙公网安备 33010602011771号