Practicalai

practicalAI-cn

AI实战-practicalAI 中文版 让你有能力使用机器学习从数据中获取有价值的见解。 🔥 使用 PyTorch 实现基本的机器学习算法和深度神经网络。 🖥️ 不需要任何设置，在浏览器中使用 Google Colab 运行所有程序。 📦 不仅仅是教程，而是学习产品级的面向对象机器学习编程。 Notebooks |基础|深度学习|进阶|主题| |-|-|-|-| |📓 Notebooks|🔥 PyTorch|📚 高级循环神经网络 Advanced RNNs|📸 计算机视觉 Computer Vision| |🐍 Python|🎛️ 多层感知 Multilayer Perceptrons|🏎️ Highway and Residual Networks|⏰ 时间序列分析 Time Series Analysis| |🔢 NumPy|🔎 数据和模型 Data & Models|🔮 自编码器 Autoencoders|🏘️ Topic Modeling| | 🐼 Pandas |📦 面向对象的机器学习 Object-Oriented ML|🎭 生成对抗网络 Generative Adversarial Networks|🛒 推荐系统 Recommendation Systems| |📈 线性回归 Linear Regression|🖼️ 卷积神经网络 Convolutional Neural Networks|🐝 空间变换模型 Spatial Transformer Networks|🗣️ 预训练语言模型 Pretrained Language Modeling| |📊 逻辑回归 Logistic Regression|📝 嵌入层 Embeddings||🤷 多任务学习 Multitask Learning| |🌳 随机森林 Random Forests|📗 递归神经网络 Recurrent Neural Networks||🎯 Low Shot Learning| |💥 k-均值聚类 KMeans Clustering|||🍒 强化学习 Reinforcement Learning| 查看 notebooks 如果不需要运行 notebooks，使用 Jupyter nbviewer 就可以方便地查看它们。 将 https://github.com/ 替换为 https://nbviewer.jupyter.org/github/ ，或者打开 https://nbviewer.jupyter.org 并输入 notebook 的 URL。 运行 notebooks 在本项目的 notebooks 文件夹获取 notebook； 你可以在 Google Colab（推荐）或本地电脑运行这些 notebook； 点击一个 notebook，然后替换URL地址中 https://github.com/ 为 https://colab.research.google.com/github/ ，或者使用这个 Chrome扩展 一键完成； 登录你自己的 Google 账户； 点击工具栏上的 复制到云端硬盘，会在一个新的标签页打开 notebook； 通过去掉标题中的副本完成 notebook 重命名； 运行代码、修改等，所有这些都会自动保存到你的个人 Google Drive。 贡献 notebooks 修改后下载 Google Colab notebook 为 .ipynb 文件； 转到 https://github.com/LisonEvf/practicalAI-cn/tree/master/notebooks ； 点击 Upload files. 上传这个 .ipynb 文件； 写一个详细详细的提交标题和说明； 适当命名你的分支； 点击 Propose changes。 贡献列表 欢迎任何人参与和完善。 |Notebook|译者| |--|--| |00_Notebooks.ipynb|@amusi| |01_Python.ipynb|@amusi| |02_NumPy.ipynb|@amusi| |03_Pandas.ipynb|@amusi| |04LinearRegression.ipynb|@jasonhhao| |05LogisticRegression.ipynb|@jasonhhao| |06RandomForests.ipynb|@jasonhhao| |07_PyTorch.ipynb|@amusi| |08MultilayerPerceptron.ipynb|@zhyongquan| |09Dataand_Models.ipynb|@zhyongquan| |10ObjectOriented_ML.ipynb|@zhyongquan| |11ConvolutionalNeural_Networks.ipynb|| |12_Embeddings.ipynb|@wengJJ| |13RecurrentNeural_Networks.ipynb|| |14AdvancedRNNs.ipynb|| |15ComputerVision.ipynb|||

PracticalAIwithSwift1stEd-Code

PracticalAIwithSwift1stEd-Code Code for the book's first edition! Email us at the authors@aiwithswift.com with questions!

PracticalAI

Practical AI for the Working Software Engineer by David M Smith (@revodavid), Cloud Advocate at Microsoft Last updated: December 4, 2018 Presented at: AI Live (AIF01), Orlando, December 7 2018 About these notebooks This library includes three notebooks to support the workshop: The AI behind Seeing AI. Use the web-interfaces to Cognitive Services to learn about the AI services behind the "Seeing AI" app Computer Vision API with R. Use an R script to interact with the Computer Vision API and generate captions for random Wikimedia images. Custom Vision with R. An R function to classify an image as a "Hot Dog" or "Not Hot Dog", using the Custom Vision service. MNIST with scikit-learn. Use sckikit-learn to build a digit recognizer for the MNIST data using a regression model. MNIST with tensorflow. Use Tensorflow (from Python) to build a digit recognizer for the MNIST data using a convolutional neural network. These notebooks are hosted on Azure Notebooks at https://notebooks.azure.com/davidsmi/projects/practicalai, where you can run them interactively. You can also download them to run them using Jupyter. Find the slides for the workshop here. Setup (for use in Azure Notebooks) Sign in to Azure Notebooks. You'll need a Microsoft Account: your O365, Xbox, or Hotmail account will work. If you're new to Notebooks, check out the Jupyter Notebook documentation and the Azure Notebook documentation. If you have an iPhone, install the free SeeingAI app. (optional) To generate keys and use Azure services, you'll need an Azure subscription. You can get a free Azure account here, with $200 in free credits for new subscribers. You'll need a credit card, but most of the things we'll use in this workshop will be free. Contact If you get stuck or just have other questions, you can contact me here: David Smith davidsmi@microsoft.com Twitter: @revodavid

pro_practicalAI

PracticalAIinUnity

Practical AI in Unity ===================== This repository is the Unity project I used for the "Practical AI in Unity" presentation - August 21st 2014 in Seattle. Running the slideshow: Open a scene, hit playmode and optionally maximize the game view by hitting space when it is focused or pinching out with the mouse over on an apple touchpad. Move through the presentation with the left/right arrow keys and the space bar. Use the shift key as modifier to skip a full slide - not going through build steps. Once started, the slideshow will always return to the last slide when entering playmode in a slide scene. To reset this behaviour, enter playmode with the "0 - Reset.unity" scene. Node editor controls: Double-click on the canvas to create a node. The name will be taken in order from the active name list ("Node #" if no name list is loaded). Create new lists from the Assets/Create menu or the Create drop-down in the project window. Double-click a node to start a connection. Right-click a node to delete it. Click and drag the canvas to move it around. Right-click and drag on the canvas horizontally or vertically to change connection orientation. The presentation recording is available here: https://www.youtube.com/watch?v=hhByGZZbcOc

Practical AI

Building on a decade of experience building AI solutions PracticalAI provides groundbreaking AI executive education cost efficient advisory services and fractional AI Officers for organizations of every size and in every industry