social practice> Types of section> Science and Technology Research Institute remote project: deep learning direction
                            Science and Technology Research Institute remote project: deep learning direction
                            Project Category: Science and Engineering Internship Research
                            Enrollment quota: 20 people
                            Suitable for groups: excellent undergraduates and sophomores and high school students with higher computer skills
                                                        Activity time: annual enrollment
register now
(Is there still a question before registration? Welcome to call customer service: 010-57952000)

project's venue:

                                Beijing

Project purpose:

                                This project aims to enable students to learn the relevant theoretical foundations of deep learning and quickly master the mainstream platform of deep learning through a combination of theory and practice. Cultivate students' innovative thinking and independent problem-solving skills, and lay a good foundation for further study and application of deep learning

project cost:

点击咨询>>

I. Project introduction

With Alpha Go in an invincible position in the professional Go competition, deep learning is invincible in the professional Go competition, deep learning is invincible in the professional Go competition, deep learning once again put artificial intelligence on A highly anticipated stage. At present, deep learning has entered the aspect of our life. It has not only achieved great success in the fields of image recognition, voice intelligent driving, etc. It has also emerged in the fields of route planning, real-time speech translation, and smart medical care. It can be said that deep learning is changing. Translation, smart medical and other fields have also emerged. It can be said that deep learning is changing, and translation, wisdom and medical fields are also emerging. It can be said that deep learning is changing our world.

In recent years, academics and industry have greatly favored talents in the field of deep learning. This course aims to comprehensively introduce the current research and application status of deep learning, elaborate the mainstream model design ideas, and combine theory with practice to use social network user modeling as a guide to guide students to quickly master the deep learning platform and methods.

After the end, the instructor will issue a recommendation letter based on the student performance.

Second, the project content

This project aims to enable students to learn the relevant theoretical foundations of deep learning and quickly master the mainstream platform of deep learning through a combination of theory and practice. The course will comprehensively introduce the current application and development trend of deep learning in text, speech and image recognition, and conduct a deep analysis of the mainstream deep learning model (taking convolutional neural networks as an example) from theoretical to concrete implementation. In addition, the course will use social network users as an application example to guide students to use the deep learning model to solve practical problems, cultivate students' innovative thinking and independent problem-solving ability, and lay a good foundation for further study and application of deep learning.

Third, the teacher background

The instructor is an associate researcher at a well-known institution of the Chinese Academy of Sciences. The main directions are data mining, deep learning, social computing, etc., and more than 30 papers have been published in internationally renowned conferences and journals such as AAAI, ICDM, and PAKDDA. Serving as the remainder of several international conferences. Serving as a multi-national conference PCchair and reviewer with a certain academic influence.

Fourth, enrollment objects and requirements

Excellent undergraduates and senior high school students with higher computer skills, plan to apply for automation, computer, software engineering, cross-disciplinary (such as business finance and other data analysis) related majors. In order to allow students to better complete research projects, the group will screen the students in the form of written test and face.

V. Itinerary

The distance of the scientific research project is one month, and the specific time can be arranged according to the needs of the students and the progress. The advantage of this project is that for students with long enough application time, the tutor can help students to complete one or more professional research tasks in a more in-depth, comprehensive and systematic manner, so that students can participate in the whole process of scientific research. Experience and solve the problem of accomplishment while giving students a deep understanding of the background and frontier dynamics of the field. In addition to the regular scientific research project discussion courses, students can ask relevant questions at any time during the period, and the professional guidance obtained will let the experience of a researcher's real work and life in advance. The course schedule is as follows:

the first week Deep learning concepts, applications and development platforms: basic, deep learning concepts, applications and development platforms: basic, deep learning concepts, applications and development platforms: basic, unified design framework for machine learning methods, several mainstream depth models ( The unified design framework of the convolutional machine learning method, several mainstream depth models (the unified design framework of the convolutional god machine learning method, the application fields and development of several mainstream depth models (convolution neural network, circulation god confrontation generation, etc.) Application fields of pre-network, cycle god confrontation generation, etc., and application fields such as pre-development network, cycle god confrontation generation, etc., and development fields of pre-development networks, cycle gods, etc.) The application field and development prospects of God's confrontation generation. Learn and master at least one deep development framework (such as the tensorflowensorflowensorflow ensorflow platform). Appointed time and Taiwan). Appointment time and students online to exchange questions and answers.
the second week Detailed explanation of convolutional neural network: For example, a detailed introduction to the traditional convolutional neural network: for example, a detailed introduction to the traditional convolutional neural network: for example, the principle of the traditional network, BP neural network, and convolution model is introduced in detail. The principle realization of the neural network and convolution model is implemented in the tensorflowensorflowensorflow ensorflow platform. Arrange students to learn relevant documents and agree on specific examples in the platform. Arrange students to learn relevant documents and agree on specific examples in the platform. Arrange students to learn relevant documents and agree on specific examples in the platform. Arrange students to learn relevant literature, and stipulate time to communicate with students online and answer questions.
The third week Introduction to social network user modeling research: Explain in detail the background of the topic, domestic social network user modeling research introduction: elaborate the background of the subject, domestic social network user modeling research introduction: elaborate the background of the subject, domestic and foreign Current status of research, introduction of traditional methods (multiple classification and labeling research status, introduction of traditional methods (multiple classification and labeling research status, introduction of traditional methods (multiple classification and labeling method)) The deep learning model solves the problem. The basic idea of ​​the method is to use the deep learning model to solve the problem. The basic idea of ​​the method is to use the deep learning model to solve the problem. The basic idea of ​​Security is to use a deep learning model to solve the problem. The basic idea of ​​Security is to use a deep learning model to solve the problem. Arrange students to learn relevant literature, stipulate time and online communication, and ask students to learn relevant documents, and agree on time and problems in online communication and give answers.
the fourth week Research on social network user modeling based on deep learning: a detailed introduction to deep learning-based social network user modeling research: detailing user-modeled data sets, related comparison algorithms, and guiding students based on user-modeled data sets, correlations The comparison algorithm guides students to implement a user image method based on convolutional neural network based on the tensorflowensorflowensorflow ensorflow platform based on user-modeled datasets and related comparison algorithms. Arrange student habits to implement a user image method based on convolutional neural networks. Arrange students to learn relevant documents, and stipulate time to communicate with students online and answer questions.