home page > Special package > AI Artificial Intelligence > Deep learning > Deep learning engineer - practical employment series

Deep learning engineer - practical employment series

The overall roadmap includes three core modules: 1. Deep learning of classic algorithms in classic fields; 2. Essential core framework for in-depth learning; 3. Comprehensive project of computer vision and natural language processing/speech recognition. It is suitable for students who are familiar with Python to join in the study. The overall style is easy to understand, and all contents are practical driven. All projects are based on real data sets and actual tasks, providing all PPT, data, and code.

nineteen

Courses

one million two hundred and eleven thousand eight hundred and forty-four

Human learning

Total course duration

Tang Yudi

Lecturer rating: 4.9

Watch for a long time

Systematic learning

Course content Q&A

Stage I: Essential classical algorithm for deep learning

3 courses ninety-eight thousand five hundred and twenty

Interpretation of core algorithms in the field of deep learning, starting from the basic neural network and gradually transitioning to the core network architecture of deep learning

Introduction to Artificial Intelligence Deep Learning Video Course
30 knots 4 hours and 59 minutes
Course objectives:
The course content mainly includes: 1. The necessary foundation of neural network; 2. Analysis of the overall architecture of neural network; 3. Implement the neural network model manually. The purpose is to lead everyone to conquer the complex neural network model step by step with the most vivid explanation. The overall style is easy to understand, leading everyone to learn deeply in a grounded way.
Course outline
Free trial
[2020 New Edition Update] Artificial Intelligence - Introduction to Deep Learning Video Course (Part 2)
24 sections 3 hours and 12 minutes
Course objectives:
This chapter mainly involves two major modules, namely, computer vision CNN network architecture and natural language processing RNN network architecture, to explain the algorithm principles and application fields of various classic network models. Explain the details of network work in detail, visually display the role of each module and its overall architecture analysis, and the style is still easy to understand, leading students to enter
Course outline
Free trial
Artificial Intelligence - Basic Mathematics Video Course
Section 129 19 hours and 11 minutes
Course objectives:
The basic mathematics course of data science and artificial intelligence aims to help students quickly lay the foundation of mathematics and explain each knowledge point in a popular way. The course content involves advanced mathematics, linear algebra, probability theory and statistics. Students should take understanding as the starting point in the learning process and do not need to memorize every formula to quickly learn the core knowledge. curriculum
Course outline
Free trial

Phase II: Deep learning core framework practice

4 courses two hundred and sixteen thousand four hundred and twenty

Classic framework practice in the field of in-depth learning, and whole process practice interpretation of the use and application examples of various frameworks

Deep learning framework - PyTorch practice
128 sections 17 hours and 37 minutes
Course objectives:
The in-depth learning framework PyTorch practical course aims to help students quickly learn the use methods of PyTorch framework core modules and project application examples, so that students can skillfully use the PyTorch framework for project development. The course content is all practical oriented, based on the current classics in computer vision and natural language processing
Course outline
Free trial
Artificial intelligence - deep learning framework - Tensorflow case practice video course
170 sections 27 hours and 37 minutes
Course objectives:
The course mainly includes two modules (principle and actual combat). At first, it will explain the major classic network architectures in in-depth learning in a popular way and give an example demonstration based on Tensorflow2 version to explain the network model training methods and strategies in detail. The actual combat of the project is all based on real data sets and actual tasks, with zero foundation, introductory, in-depth learning and TF
Course outline
Free trial
In depth learning Keras project practice
78 sections 11 hours and 18 minutes
Course objectives:
Course introduction: The Keras project practical course starts from the point of view of actual combat, based on real data sets and actual business needs, explains how to conduct data processing, model training and optimization from scratch, and finally carries out testing and results display and analysis. The whole process of practical operation, in a very grounded way to explain each step of the process and solution. Curriculum integration
Course outline
Free trial
Big data - deep learning framework Caffe use case video course
Section 13 3 hours and 35 minutes
Course objectives:
Introduction to the deep learning framework coffee, which explains the structure and parameter items of each layer in the network configuration in detail, and explains the meaning and selection strategy of each parameter for the super parameter configuration file. For the data source instance, the two most commonly used data source LMDB and HDF5 formats are demonstrated. The course involves many tips of caffe framework, such as drawing
Course outline
Free trial

Stage 3: Deep learning - big project practice

12 courses five hundred and twenty-seven thousand two hundred and eighty

Classic projects in the field of deep learning are all based on real data sets and actual tasks, and the whole process of debugging is to interpret the details of source code implementation.

Intensive Learning Practice Series (2020 New Edition)
83 sections 10 hours and 28 minutes
Course objectives:
The intensive learning series courses mainly include two parts: explanation of classic algorithm principles and case practice. Popularly explain the current mainstream reinforcement learning algorithm ideas, interpret the algorithm with examples, sort out the application process and conduct code practice with examples. The overall style is easy to understand, suitable for students who are preparing for entry, intensive learning and advanced promotion.
Course outline
Free trial
In depth learning - pedestrian recognition practice (2020 new version)
Section 91 12 hours and 22 minutes
Course objectives:
The course of pedestrian recognition mainly includes three core modules: 1.2020 Detailed interpretation of classic algorithms (papers); 2. Project source code analysis; 3. Practical application; Popular explanation of the latest pedestrian re identification direction algorithm and its implementation in conferences such as CVPR, and actual combat based on PyTorch framework, line by line explanation of all project source codes and their applications
Course outline
Free trial
In depth learning - speech recognition project practice (Python version)
Section 97 12 hours and 49 minutes
Course objectives:
The practical course of speech recognition based on deep learning mainly includes three parts: 1. explanation of algorithms in classic papers; 2. Interpretation of algorithm source code; 3. Project practice; Popular explanation of the current classic paper ideas in the field of speech recognition, detailed interpretation of each core module in the source code, and project practice based on real data sets. The overall course covers speech recognition
Course outline
Free trial
Deep learning - confrontation generation network practice series
Section 86 11 hours and 25 minutes
Course objectives:
The actual combat series of confrontation generation network mainly includes three core contents: 1. Interpretation of classic GAN papers; 2. Interpretation of source code reproduction; 3. Practical application of the project. Comprehend the construction and application methods of various classic GAN models in the whole process, explain the core knowledge points in the paper and the overall network model architecture in a popular way, starting with data preprocessing and environment configuration
Course outline
Free trial
Example of deep learning model deployment and pruning optimization
Section 66 8 hours and 35 minutes
Course objectives:
The in-depth learning model deployment and pruning optimization example course aims to help students quickly learn model deployment and optimization methods. It mainly includes two core modules: 1. Demonstrate the model deployment method based on the deep learning framework PyTorch and Tensorflow 2, and use docker tools to simplify the environment configuration and migration
Course outline
Free trial
Deep learning - object detection - YOLO practical series (updated V5)
Section 101 13 hours and 46 minutes
Course objectives:
The YOLO series courses of object detection mainly include two core modules: (1) The YOLO series algorithms are elaborated, the core knowledge points and the overall network architecture of the YOLO series are explained in detail, and their effects are analyzed in depth, and the implementation principles and effect improvement details of the YOLO architecture are explained in general; (1) , YOLO-V3 and latest V
Course outline
Free trial
In depth study of classic papers and open source project practice
Section 134 20 hours and 15 minutes
Course objectives:
The course of in-depth learning classic thesis interpretation and project practice aims to help students learn the core thesis ideas and source code implementation in the current in-depth learning field. The selected papers are mainstream general algorithms in the field of computer vision and natural language processing, and the main contents include four core parts: 1. Interpretation of the core ideas of the paper; 2. Detailed knowledge points of the paper
Course outline
Free trial
Python - Deep Learning - Object Detection Practice
40 knots 6 hours and 24 minutes
Course objectives:
Computer Vision Object Detection General Solution Framework Mask Rcnn practical course aims to help students quickly learn the current mainstream solutions and network framework construction principles in the field of object detection, and interpret its application fields and methods based on open source projects. The core source code of each module in the project is interpreted in detail through debug,
Course outline
Free trial
Python Natural Language Processing - BERT Practice
53 sections 7 hours and 55 minutes
Course objectives:
The Python natural language processing BERT model practice course aims to help students quickly learn the principle construction and application examples of BERT, the core algorithm model in the NLP field. Popular explanation of the core knowledge points involved in the BERT model (Transformer, self attention
Course outline
Free trial
Ai Engineer - Natural Language Processing Practice (Python Version)
Section 209 36 hours and 45 minutes
Course objectives:
AI Engineer - Natural Language Processing Practical Course aims to explain complex algorithm principles in the most grounded way. Based on real data sets, project practice is carried out through actual cases. The whole system includes 200+class hours and 20 projects, covering the current popular technology and classic framework. The learning route mainly includes three stages: 1
Course outline
Free trial
Big data: deep learning project practice - key point positioning video course
12 sections 2 hours and 54 minutes
Course objectives:
In depth learning project practice - key point positioning course takes face key point detection as the background, selects a multi-stage detection network architecture, and selects hdf5 as the input data source of the network for regression and multi label label problems. An example demonstrates how to make a multi label data source and enhance the original data. The whole network architecture adopts three
Course outline
Free trial
Big data: deep learning project practical video course - face detection
16 sections 2 hours 50 minutes
Course objectives:
The in-depth learning project practice course starts from the common face detection project, and generally understands the nature of the project and the accompanying challenges. Starting from data collection and pre-processing, we lead you step by step to complete the entire face detection project, which involves how to use the deep learning framework Caffe to complete the architecture of the entire project. After completing the code
Course outline
Free trial