Deep Learning : From Scratch To The Depth

为了回避个人电脑的不折不扣的想法，复杂而多样的深度大脑网络被构建并用作学习的基础。深度学习模型不是作为一个顺序程序工作，而是利用由集线器连接的网络来工作——就像人类大脑如何利用大量相关的神经元来工作一样。它是设计进步、最佳实践和假设的融合，为大量以前难以想象的精明应用提供了支持。尽管它是可编程机器，但深度学习框架不会像普通 PC 那样处理信息。一个单独的深度大脑网络由多个层次组成——层次越多，结果就越准确。尽管如此，他们不是独立工作或交替工作，而是扩展彼此的工作。虽然大脑网络因工作方式而波动，并且并非每个人都以直接的设计处理信息，但它们都有一个比较的基础。鉴于过去图层的预测和分类，改进和简化了再现。机器在层内所做的工作大部分都被掩盖了，除了信息和结果层，也称为“表观层”。

概述

第 1 节：简介

第 1 讲 深度学习简介

第 2 讲深度学习简介——神经网络

第 2 节：深度学习模型

第 3 讲深度学习模型 – 基础知识

第 4 讲深度学习模型——详细

第 5 讲深度学习模型——神经网络及其特征

第 6 讲深度学习模型——神经网络及其特点

第 7 讲深度学习模型——神经网络及其特征

第 3 节：附加模型

第 8 讲其他深度学习模型 – 第 1 部分

第 9 讲其他深度学习模型——第 2 部分

第 10 讲额外的深度学习模型——生成对抗网络 (GAN)

第 4 节：图书馆

第 11 讲 深度学习平台库——基础

Lecture 12 深度学习平台库——基础

Lecture 13 深度学习平台库 – DataGraph Lab

Lecture 14 深度学习平台库——DataGraph Lab 结论

第 15 讲 深度学习平台库——Theano 和 Caffe

第 16 讲深度学习平台库 – TensorFlow 第 -1 部分

第 17 讲深度学习平台库 – Theano 或 TensorFlow 第 2 部分

对深度学习和数据科学感兴趣的 Python 开发人员、编程爱好者、希望扩大 Python 技能的学生

Published 6/2022
MP4 | Video: h264, 1280×720 | Audio: AAC, 44.1 KHz
Language: English | Size: 4.52 GB | Duration: 8h 43m

Complete package of deep learning

What you’ll learn
Classify images, data, and sentiments using deep learning
Make predictions using linear regression, polynomial regression, and multivariate regression
Data Visualization with MatPlotLib and Seaborn
Clean your input data to remove outliers
Advanced usage of python
Requirements
Just a basic understanding of programming. We’ll take care of the rest !!
Description
To sidestep the unbending idea of PCs, complex and diverse profound brain networks are constructed and utilized as a base for learning. Rather than working as a sequential program, profound learning models work utilizing networks joined by hubs — like how the human mind utilizes a large number of associated neurons to work. It’s the blend of designing advances, best practices, and hypotheses that empowers an abundance of beforehand unimaginable savvy applications.Regardless of as yet being a programmable machine, profound learning frameworks don’t deal with information like your normal PC. A solitary profound brain network comprises various layers — the more layers there are, the more exact the outcomes. Be that as it may, rather than working independently or alternating, they expand upon one another’s work. While brain networks fluctuate by the way they work, and not every one of them process information in a straight design, they all have a comparative establishment.‌Rather than working with the crude information of the info once more, each layer works with a somewhat more refined and streamlined rendition in view of the past layer’s forecast and classification. The work the machine does inside the layers remains for the most part covered up, except for information and result layers, otherwise called the ‘apparent layers’.

Overview

Section 1: INTRODUCTION

Lecture 1 Introduction to Deep Learning

Lecture 2 Introduction to Deep Learning – neural networks

Section 2: DEEP LEARNING MODELS

Lecture 3 Deep Learning Models – basics

Lecture 4 Deep Learning Models – DETAILED

Lecture 5 Deep Learning Models – neural network and its characteristics

Lecture 6 Deep Learning Models – neural network and its characteristics

Lecture 7 Deep Learning Models – neural network and its characteristics

Section 3: ADDITIONAL MODELS

Lecture 8 Additional Deep Learning Models – Part 1

Lecture 9 Additional Deep Learning Models – Part 2

Lecture 10 Additional Deep Learning Models – Generative Adversarial Networks (GAN)

Section 4: LIBRARIES

Lecture 11 Deep Learning Platforms Libraries – basics

Lecture 12 Deep Learning Platforms Libraries – basics

Lecture 13 Deep Learning Platforms Libraries – DataGraph Lab

Lecture 14 Deep Learning Platforms Libraries – DataGraph Lab Conclusion

Lecture 15 Deep Learning Platforms Libraries – Theano and Caffe

Lecture 16 Deep Learning Platforms Libraries – TensorFlow part -1

Lecture 17 Deep Learning Platforms Libraries – Theano or TensorFlow Part – 2

Python developers curious about deep learning and data science,Programming enthusiasts,Students who wish to broaden their skillsets in python