Tag：Deep learning
-
Time：2020-3-19
It’s a great pleasure to announce our new project: Mars, a matrix based unified distributed computing framework. We have open source at GitHub: https://github.com/mars-project/mars. background Python Python is a quite ancient language. Nowadays, Python is becoming more and more popular in the fields of data science computing, machine learning, and deep learning. In the field […]
-
Time：2020-3-5
Abstract:The research and development team of maxcompute, Alibaba’s unified big data computing platform, has gone through more than one year’s research and development, broken the boundaries of big data and scientific computing, completed the first version and opened it to the public. Mars, a unified distributed computing framework based on tensor. Using Mars for scientific […]
-
Time：2020-3-4
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 […]
-
Time：2020-2-23
1、 Background: born out of nowhere, Bert transcends human beings in an all-round way In 2018, the most explosive “mushroom cloud” in the field of natural language processing (NLP) is the Bert (bidirectional encoder representations from transformers) model proposed by Google research. As a new language representation model, Bert has swept the laurels of NLP […]
-
Time：2020-2-22
1 Comparison of mainstream deep learning framework Today’s software development is basically hierarchical and modular, and the application layer development will be based on the framework layer. For example, the development of Linux driver will be based on Linux kernel, and the development of android app will be based on Android framework. Deep learning is […]
-
Time：2020-2-12
Neural network, supervised learning and in-depth learning belong to the author’s deep learning specialization course notes series. This paper mainly describes the notes and code implementation of the author’s learning Andrew ng deep learning specialization series. Neural network, supervised learning and deep learning Deep learning is gradually changing the world, from traditional Internet businesses such […]
-
Time：2020-2-11
Notes on Andrew ng deep learning: gradient descent and vectorization are subordinate to the author’s series of notes on deep learning specialization. This paper mainly describes the notes and code implementation of the author’s series of notes on Andrew ng deep learning specialization. Note that this article has a large number of mathematical symbols and […]
-
Time：2020-2-10
Written in front This will be a long article, which not only includes the explanation of the implementation process of karpath’s natural network, but also Andrew NG’s explanation of softmax. Author : JasperyangSchool : BUPT text Start with natural networks case study This part is directly the translation of neural networks case study. I think […]
-
Time：2020-2-8
Problem introduction Imagine that an object itself and a collection of objects need to support the same operation logically, and the actual implementation may be different. Since the higher-level abstraction of semantics can unify the two, wouldn’t it be better if both inherit the same base class? An analogy is that the directory itself may […]
-
Time：2020-2-8
The input adopts placeholder, the model receives any length vector, calculates the total output of data flow graph over time, reasonably divides the data flow graph by name scope, saves the output, accumulation and mean value of data flow graph to disk every time. [none] for any length vector, [] for scalar. The update phase […]
-
Time：2020-2-7
Welcome to Tencent cloud community to get more Tencent technology practice dry goods~ Author: Duan Shishi Preface Some time ago, because of the needs of the project, I began to contact with NLP. I felt that I was not a professional, and I didn’t understand a lot of things very well. So I took the […]
-
Time：2020-2-5
Neural style is a very interesting deep learning application: input a picture representing the content and a picture representing the style, and the deep learning network will output a new work integrating the style and content. Tensorflow is Google’s most popular open source deep learning framework. Author anishatalye uses tensorflow to implement the neural style […]
