Tag:neural network

  • Machine learning milestone: Google open source tensorflow 0.8 fully realizes parallel computing and combines original ecological support with kubernetes


    Recently, Google officially announced that tensorflow 0.8 has fully realized parallel computing and the combination of original ecological support and kubernetes, which makes the open-source project tensorflow of Google machine learning achieve a qualitative leap in supporting clustering, parallelism and distributed training. In Google’s official blog last week, Google announced the acceleration effect that different […]

  • Introduction to deep learning: 10 free online courses recommended


    Give into deep learning, in-depth learning has always been a hot topic in the audio and video industry. Here are 10 free quality online courses recommended.We recommend you to open source project class central, which has 31 online courses (10 of which are completely free), covering from the foundation of in-depth learning to the most […]

  • Tensorflow 2 quick tutorial, a must for beginners


    About tensorflow 2 Tensorflow is a deep learning open source tool released by Google in November 2015. We can use it to quickly build deep neural networks and train deep learning models. The main purpose of using tensorflow and other open source frameworks is to provide us with a module toolbox that is more conducive […]

  • Auto keras and automl: Getting Started Guide


    Abstract:No machine learning? Not AI? No problem! Here comes the automation! In this tutorial, you will learn how to use auto keras (Google’s open source alternative to automl) for automated machine learning and deep learning. At present, deep learning practitioners are trying to optimize and balance two objectives when training neural networks on datasets: 1.DefinitionSuitable […]

  • NLP tutorial: how to automatically generate couplets


    Demo: https://www.flyai.com/couplets The most important feature of the recurrent neural network is that it can take the sequence as input and output, and the up and down links of the couplet are typical sequence words. So, can we use the neural network to carry out the couplet? The answer is yes. In this project, the […]

  • On the concept of neural network


    I have contacted and understood the related concepts of neural network before, but I haven’t made any systematic summary. In this period of time, I will summarize the related concepts;For the concept of neural network, the most important is some related understanding concepts: back propagation, activation function, regularization and batchnomalizim. 1、 Back propagation:In fact, back […]

  • Getting started with AI


    I. Introduction 1. What is artificial intelligence? If you are a fan of new technology or a student of engineering, you must have heard of artificial intelligence (AI). For what is artificial intelligence, baidu defines it as follows: Artificial intelligence, abbreviated as AI. It is a new technology science to research and develop the theory, […]

  • Euler is out today! The first industrial in-depth learning open source framework in China, made by Ali mom


    Sister Ali:Don’t come out until you call! Ali’s mother officially announced the heavyweight open source project, the in-depth learning framework Euler. This is the first in-depth graph learning framework that is open-source after large-scale application of core business in China. In this open source, Euler has built in a large number of algorithms for users […]

  • Tensorflower (I)


    The handwritten numbers in MNIST dataset are 28×28 pixel gray-scale images. The simplest way to classify them is to use 28×28 = 784 pixels as the input of 1-layer neural network.Each “neuron” in the neural network will add a constant called “Deviation” to the weighted sum of all its inputs, and then extract the results […]

  • Machine learning notes (3)


    1、 The basic structure of neural networks The neural network is built up by the neural layer. It consists of input layer, hidden layer and output layer. The input layer is the input of the feature; the hidden layer has many layers, including the new features generated by the neural network (multiple combinations of input […]

  • Image color extraction


    This article GitHub project: colorfull color My codepen link: image color extractionthe demo Original article, reprint please indicate Recently, I want to find a small project to practice so that I can be familiar with react, so I came up with the direction of “image color extraction”, which is also said to beImage theme color […]

  • Alibaba cloud front end Weekly – issue 16


    Recommend 1. introduction to neural network http://www.ruanyifeng.com/blo… At present, the most popular technology is artificial intelligence. The underlying model of artificial intelligence is neural network. Many complex applications (such as pattern recognition, automatic control) and advanced models (such as deep learning) are based on it. Learning artificial intelligence must start from it. 2. React Redux […]