sigma

dynamic release comment Friends about
  • theme reply curriculum data Reference design Circuit diagram article Blog

    1. Mobile platform deep neural network practice: principle, architecture and optimization

      label: neural network Deep learning

      This book focuses on the core algorithm, hardware level instruction set, system design and programming practice, massive data processing, industry popular framework tailoring and product level performance optimization strategies required by the mobile platform deep learning system. The foundation of deep learning (Chapter 1-4) introduces the important knowledge points required for developing machine learning systems, and the algorithm cornerstone of developing mobile platform machine learning systems, such as artificial neural networks, sparse self encoders, deep networks, convolutional neural networks, etc. The foundation of mobile platform deep learning (Chapter 5-6) introduces the construction of mobile platform development environment, the foundation of mobile platform development, ARM instruction set acceleration technology, and the implementation principle and practice of lightweight network. Deeply understand deep learning (Chapters 7-8), analyze the principles and methods of data preprocessing, develop high-performance real-time processing systems, and detect and recognize objects based on deep neural networks. This is the precursor and "cornerstone" of the next article. Deeply understand mobile platform deep learning (Chapters 9-12). This chapter applies the framework and technology of the previous chapters to realize the realization and integration of mobile platform deep learning system, specifically covering: ① mobile platform performance optimization, data acquisition and training, to establish the foundation for the development of mobile platform image classification system; ② Deeply analyze TensorFlow Lite code system, construction principle, integration method, core code and tailoring analysis, model processing tools, and complete mobile platform system integration; ③ Analyze the machine learning framework and interface of mainstream mobile platforms based on actual combat, and look forward to the future.

      amount of downloads 4 times Resource Type Technical Documentation Upload time: June 20, 2024

    2. Deep Learning for Natural Language Processing: Creating Neural Networks with Python

      label: natural language processing Deep learning Python neural network

      The book is divided into five chapters. Through introducing complete examples of neural network models (including recurrent neural networks, long-term and short-term memory networks, and sequence to sequence models), it explains to readers the concept of deep learning for natural language processing (NLP). The first three chapters introduce the basic knowledge of NLP and deep learning, word vector representation and advanced algorithms. The last two chapters focus on the implementation process, and use Python tools TensorFlow and Keras to deal with complex architectures, such as RNN, LSTM and seq2seq. This book follows the step-by-step method, and finally gathers all the knowledge to build a question and answer chat robot system.

      amount of downloads 3 times Resource Type Technical Documentation Upload time: June 20, 2024

    3. Graphic Deep Learning and Neural Networks: From Tensor to TensorFlow Implementation

      label: Deep learning neural network TensorFlow

      This book is an introduction to neural networks and deep learning using TensorFlow as a tool. The content is step-by-step. In the form of simple examples and illustrations, it shows the basic mathematical principles behind neural networks and deep learning to help readers better understand complex and abstract formulas. At the same time, using manual calculation and program code to explain examples can better help readers understand the common function interfaces of TensorFlow and lay a good foundation for readers to master the use of TensorFlow to build AI projects. This book is suitable for beginners of neural network, deep learning and TensorFlow.

      amount of downloads 7 times Resource Type Technical Documentation Upload time: June 20, 2024

    4. Analytic Deep Learning: Convolution Neural Network Principle and Visual Practice

      label: Deep learning Convolutional neural network

      As an introductory book in this field, this book covers the basic knowledge and practical application of deep convolutional neural networks. The book consists of 14 chapters and is divided into three parts: the first part is the introduction; The second part (Chapters 1-4) introduces the basic knowledge, basic components, classical structure and model compression of convolutional neural network; The third part (Chapters 5-14) introduces the practical application skills and experience of deep convolution neural network from data preparation to model parameter initialization, selection of different network components, network configuration, network model training, unbalanced data processing, and finally to model integration. This book is not a programming book, but hopes to enable readers to understand, master and successfully build a deep convolutional neural network for their own application problems from a higher dimension through "basic knowledge" and "practical skills". This book can be used as an introductory book for deep learning and convolutional neural network enthusiasts, and can also be read for practitioners in all walks of life who do not have a machine learning background but want to quickly master this knowledge and apply it to practical problems.

      amount of downloads 7 times Resource Type Technical Documentation Upload time: June 20, 2024

    5. Neural Network and Deep Learning -- Implementation Based on TensorFlow Framework and Python Technology

      label: neural network Deep learning TensorFlow Python

      Python、TensorFlow、 Neural networks and deep learning have become popular keywords in the IT field due to the popularity of artificial intelligence. This book first introduces the basic usage of Python and its common libraries Numpy, Matplotlib and Scipy; Secondly, it introduces the basic knowledge and usage of TensorFlow; Then it introduces the basic knowledge of neural network and the basic application of neural network - perceptron, linear regression and logical regression theory and implementation; Finally, the theory and implementation of two popular deep neural networks, convolutional neural network and cyclic neural network, are introduced. The content of this book is from simple to deep, step-by-step, practical, and contains rich simulation examples.

      amount of downloads Once Resource Type Technical Documentation Upload time: June 20, 2024

    6. TensorFlow in-depth learning from beginner to advanced

      label: TensorFlow Deep learning

      This book takes TensorFlow as the main line to explain. Each chapter in the book is led out by theory, and ends with the consolidation of TensorFlow application. The combination of theory and practice enables readers to quickly master TensorFlow machine learning. This book has 11 chapters, mainly including TensorFlow and Deep Network, TensorFlow Programming Foundation, TensorFlow Programming Advanced, Linear Regression, Logical Regression, Clustering Analysis, Neural Network Algorithms, Convolution Neural Network, Cyclic Neural Network, Other Networks, Machine Learning Comprehensive Practice, etc.

      amount of downloads 3 times Resource Type Technical Documentation Upload time: June 20, 2024

    7. 100 sided in-depth learning: algorithm engineer takes you to interview

      label: Deep learning artificial intelligence algorithm

      Deep learning is a hot topic in academia and industry, and has been successfully applied in many industries. This book is jointly written by nearly 30 algorithm researchers and algorithm engineers in Hulu. It is specifically aimed at the field of deep learning, and is an extension of Hundred Faces Machine Learning: Algorithm Engineers Take You for Interviews. The whole book is roughly divided into two parts. The first part introduces classical deep learning algorithms and models, including convolutional neural network, cyclic neural network, graph neural network, generation model, generative confrontation network, reinforcement learning, meta learning, automatic machine learning, etc; The second part introduces the application of deep learning in some fields, including computer vision, natural language processing, recommendation system, computational advertising, video processing, computer hearing, automatic driving, etc. The book still uses the form of question and answer of knowledge points to organize the content, and each question gives the difficulty level and relevant knowledge points to urge the readers to conduct self-examination and active thinking. Each chapter in the book carefully selects the problems in different aspects and levels of the corresponding fields, matches with each other, and shows the "hundred aspects" of in-depth learning, so that different readers can find appropriate content. This book is suitable for students of relevant majors to check and strengthen their mastery of the knowledge points they have learned. Job seekers can quickly review and supplement relevant in-depth learning knowledge, and algorithm engineers can refer to it as a reference book at any time. In addition, researchers who are not related majors but are interested in AI or deep learning can also learn about some popular AI applications, core algorithms behind deep learning models and their ideas through this book.

      amount of downloads Twice Resource Type Technical Documentation Upload time: June 20, 2024

    8. Deep learning architecture: mathematical methods

      label: Deep learning neural network

      This book describes the operation of neural networks from a mathematical perspective. Considering that the success of neural network methods should not be determined by trial and error or luck, but by clear mathematical analysis. The main goal of this work is to express the ideas and concepts of neural networks currently used at the intuitive level with accurate modern mathematical language. This book is a mixture of classical mathematics and deep learning of modern concepts. Mainly focus on mathematics, because in today's development trend, many mathematical aspects are ignored, and most papers only emphasize the details of computer science and practical applications.

      amount of downloads 7 times Resource Type Technical Documentation Upload time: June 20, 2024

    9. Introduction to Mathematics of Deep Learning: Methods, Realization and Theory

      label: Deep learning

      This book aims to introduce the topic of deep learning algorithm. Roughly speaking, when we talk about deep learning algorithm, we think of a calculation scheme, which aims to approximate some relations, functions or quantities through the so-called deep artificial neural network (ann) and the iterative use of some data. On the contrary, artificial neural networks can be considered as a function class composed of multiple combinations of some nonlinear functions (called activation functions) and some affine functions. Roughly speaking, the depth of this artificial neural network corresponds to the number of iterative combinations involved in the artificial neural network. When the number of combinations involved in nonlinear and affine functions is greater than 2, people begin to talk about deep artificial neural networks. We hope that this book is useful for students and scientists who have no deep learning background and hope to gain a solid foundation, as well as practitioners who hope to gain a more solid mathematical understanding of the objects and methods considered in deep learning.

      amount of downloads 4 times Resource Type Technical Documentation Upload time: June 20, 2024

    10. Neural Network and Deep Learning Practice Python+Keras+TensorFlow

      label: neural network Deep learning

      This book leads readers into the door of artificial intelligence technology through the combination of theory and project practice. The book starts with the mathematical basis of AI technology, then focuses on the analysis of the operation process of neural networks, and finally helps readers to grasp the basic theoretical knowledge and core development technology required for AI development in a solid way through a large number of practical project coding practices. This book has 15 chapters, covering the initial experience of neural networks; Calculus foundation of deep learning; Linear algebra basis of deep learning; The theoretical basis of neural network; Using Python to realize the neural network of recognizing handwritten numerals from zero; Neural network project practice; Using neural network to realize machine vision recognition; Realizing natural language processing with deep learning; Automatic encoding and decoding network and generative adversarial network; The development practice of reinforcement learning network; TensorFlow Introduction; Develop advanced natural language processing system using TensorFlow and Keras; Use TensorFlow and Keras to realize the advanced image recognition processing system; Use TensorFlow and Keras to build an intelligent recommendation system; Summary of important concepts and skills for in-depth learning. This book tries to reduce the threshold for readers to learn AI programming through detailed explanation. The book is rich in cases and very practical, especially suitable for IT professionals or students who are interested in the field of artificial intelligence. Reading this book requires readers to have a certain mathematical foundation.

      amount of downloads 3 times Resource Type Technical Documentation Upload time: June 20, 2024

    11. Deep learning: the core driving force in the intelligent era

      label: Deep learning artificial intelligence

      Global technology giants have embraced deep learning. Behind automatic driving, AI medical, voice recognition, image recognition, intelligent translation and the world shaking AlphaGo, deep learning plays a magical role. Deep learning is the mainstream technology of AI from concept to prosperity. Computers that have undergone in-depth learning and training no longer operate passively according to instructions, but begin to learn from experience independently, just like naturally evolving life. The author of this book is one of the top ten global AI scientists, the pioneer and founder of deep learning, and has experienced the winter of deep learning in the 1970s and 1990s. But he and a group of pioneers, using big data and increasing computing power, finally made a major breakthrough in neural network algorithm and achieved blowout development of artificial intelligence. As a general knowledge work in the field of deep learning, this book shows the development, evolution and application of deep learning through three parts of panorama in a magnificent way. For the first time, it traces back the development context of deep learning wave and the spiral rise of artificial intelligence in the past 60 years from the perspective of an experienced person, and forecasts the business prospect of the intelligent era prospectively.

      amount of downloads 3 times Resource Type Technical Documentation Upload time: June 20, 2024

    12. Machine learning programming: from coding to deep learning (English)

      label: machine learning Deep learning

      Programming Machine Learning: From Coding to Deep Learning By Paolo Perrotta You have decided to enter the field of machine learning - because you are looking for a job, starting a new project, or just thinking that autonomous cars are cool. But where do we start? Even software developers are easily afraid. The good news is that this is not difficult. Master machine learning by writing one line of code at a time, from simple learning programs to real deep learning systems. By breaking down difficult problems, we can make them easier to understand, and build confidence by doing it yourself. From the beginning to the depth of learning, the obscurity of machine learning is uncovered. Machine learning can be daunting because it relies on mathematics and algorithms that most programmers will not encounter in their daily work. Take a hands-on approach, write your own Python code, and don't use any library to cover up what really happened. Iterating your design and adding complexity to the process. Use supervised learning to build image recognition applications from scratch. Use linear regression to predict the future. Deeply study gradient descent, which is the basic algorithm driving most machine learning. Create perceptrons to classify data. Construct neural networks to process more complex and precise data sets. Use backpropagation and batch processing to train and optimize these networks. Hierarchical neural network, eliminate over fitting, and add convolution to turn your neural network into a real deep learning system.

      amount of downloads Once Resource Type Technical Documentation Upload time: June 17, 2024

    13. In depth learning guide

      label: Deep learning

      The author of Deep Learning For Dummies is John Paul Mueller, Luca Massaron Deep learning provides a way to identify data patterns and promotes the development of online businesses and social media. Introduction to Deep Learning provides you with the information you need to uncover the mystery of this topic - as well as all the underlying technologies related to it. Soon, you will understand these increasingly confusing algorithms and find a simple and safe environment to try deep learning. This book enables you to understand what deep learning can do at a high level, and then provides examples of the main types of deep learning applications.

      amount of downloads 0 times Resource Type Technical Documentation Upload time: June 17, 2024

    14. NVIDIA Full Color Deep Learning Guide

      label: Deep learning

      Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, Natural Language Processing, and Transformers Using TensorFlow Deep learning (DL) is a key component of today's exciting advances in machine learning and artificial intelligence. Learning in Depth is a complete DL guide. This book clarifies the core concepts and hands-on programming techniques required for success, which is very suitable for developers, data scientists, analysts and other personnel - including those without machine learning or statistical experience. After introducing the basic building blocks of deep neural networks (such as artificial neurons and full connection, convolution and circulation layers), Magnus Ekman showed how to use them to build advanced architectures, including Transformer. He described how to use these concepts to build modern networks for computer vision and natural language processing (NLP), including Mask R-CNN, GPT and BERT. He also explained how natural language translators and systems generate natural language descriptions of images.

      amount of downloads Twice Resource Type Technical Documentation Upload time: June 17, 2024

    15. Deep Learning Mathematics: Understanding Neural Networks

      label: Deep learning neural network

      Math for Deep Learning: What You Need to Know to Understand Neural Networks by Ronald T. Kneusel Deep Learning Mathematics provides the basic mathematical knowledge you need to understand deep learning discussions, explore more complex implementations, and better use the deep learning toolkit. Through Deep Learning Mathematics, you will learn the basic mathematical knowledge and background knowledge used in deep learning. You will learn key in-depth learning related topics in probability, statistics, linear algebra, differential calculus and matrix calculus through Python examples, as well as how to realize data flow in neural networks, back-propagation and gradient descent. You will also use Python to study the mathematical knowledge behind these algorithms, and even build a fully functional neural network. In addition, you will also learn about gradient decline, including variants commonly used by the deep learning community: SGD, Adam, RMSprop, and Adagrad/Adadelta.

      amount of downloads 4 times Resource Type Technical Documentation Upload time: June 17, 2024

    16. Neural Network and Deep Learning (Qiu Xipeng)

      label: neural network Deep learning

      Neural Network and Deep Learning Author: Qiu Xipeng This is a book that explains how to build a user portrait system from 0 to 1 from the perspective of technology, product and operation. It also provides a solution for how to use the user portrait system to drive the revenue growth of enterprises. The author has many years of experience in big data R&D and data-driven operation, participated in and was responsible for the construction of a number of hundred million scale user portrait systems, and has rich experience in the design, development and landing solutions of user portrait systems. There are nine chapters in the book: Chapters 1 to 6 mainly explain the concepts, technologies, processes and methodologies that need to be mastered to build a user portrait system, including the basic knowledge of user portrait, data index system, label data storage, label data development, development performance optimization, job process scheduling, etc; Chapter 7 explains how to product user portraits to provide solutions for engineering practice; Chapter 8 explains in detail the application of user portraits in three classic fields: business analysis, precision marketing and personalized recommendation; Chapter 9 explains the landing cases of eight user portrait systems through eight common scenarios, to help readers master how to use user portrait systems to drive revenue growth of enterprises.

      amount of downloads Once Resource Type Technical Documentation Upload time: June 17, 2024

    17. Keras quick start: deep learning practice based on Python

      label: Keras Python Deep learning

      Author: Xie Liang, Lu Ying, Lao Honglan; Published in 2017 Keras Get Started Quickly: Python based Deep Learning Practice systematically explains the basic knowledge, modeling process and application of deep learning, and takes the specific application of deep learning in recommendation systems, image recognition, natural language processing, text generation and time series as an example to introduce in detail the following aspects: tool preparation The whole process and practical experience from data acquisition and processing to problem modeling is a very good primer for in-depth learning.

      amount of downloads Once Resource Type Technical Documentation Upload time: June 17, 2024

    18. Discrete Mathematics Fundamentals, Algorithms and Programming

      label: discrete mathematics

      Foundations of Discrete Mathematics with Algorithms and Programming Discrete mathematics has penetrated into the whole mathematical field, so that now even in high school, it has begun to teach it. This book introduces the basic knowledge of discrete mathematics and its application in daily problems in many fields. This book is intended for undergraduates majoring in computer science, mathematics and engineering. The book gives many examples to deepen the understanding of concepts. The programming languages used are Pascal and C.

      amount of downloads Once Resource Type Technical Documentation Upload time: June 17, 2024

    19. Random Matrix Method for Machine Learning

      label: machine learning Random matrix

      Random Matrix Methods for Machine Learning Author: Romain Couillet, Zhenyu Liao This book introduces the unified theory of random matrix for machine learning applications, and provides a high-dimensional data vision using concentration and universality. This makes it possible to accurately understand and possibly improve the core mechanism that plays a role in the real world machine learning algorithm. This book first comprehensively introduces the basic theoretical knowledge of random matrix, which provides support for a wide range of applications, from support vector machines to semi supervised learning, unsupervised spectral clustering and graph methods, to neural networks and deep learning. For each application, the author discussed the small dimension and large dimension intuition of the problem, and then the author conducted a systematic random matrix analysis of the result performance and possible improvements.

      amount of downloads Twice Resource Type Technical Documentation Upload time: June 17, 2024

    20. Vision perception and control of robot system based on multi view geometry

      label: visual perception Deep learning

      Multi View Geometry Based Visual Perception and Control of Robotic Systems Author: Jian Chen, Bingxi Jia , Kaixiang Zhang This book describes the visual perception and control methods of robot systems that need to interact with the environment. Multi view geometry is used to extract low dimensional geometric information from rich high-dimensional image information, which facilitates the development of universal solutions for robot perception and control tasks. In this book, multi view geometry is used for geometric modeling and scaling pose estimation. Then the Lyapunov method is applied to design the stable control law in the presence of model uncertainty and multiple constraints.

      amount of downloads 0 times Resource Type Technical Documentation Upload time: June 17, 2024

Section one page home page Last page Total three page Jump

Recent Visitors

< one / six >

statistical information

already existing six hundred and eighty-six People have visited

  • Core integral: 12884
  • Friend: 1
  • Subject: 80
  • Re: 15

Leaving a message.

You need to log in before you can leave a message Sign in | register

Eolian quicksand 2024-3-8
Downloaded your information, thank you for sharing
yinhu0 2023-6-14
Design and Implementation of a 64 bit Operating System requires an open password
Lao Xie 2021-10-25
Send an attachment
biaobiao2019 2021-7-19
Research on the Application of Machine Learning in Quantitative Investment has been downloaded twice, and the problem is the same. Please upload it again.

There is a problem with the document of this book. It cannot be seen after 114 pages.
fankai 2018-3-30
There is a problem with the document of the book "Research on the Application of Machine Learning in Quantitative Investment". It is not visible after 114 pages. It has been downloaded twice. The problem is the same. Please upload it again.
View All

Recommended Blog