Deep Learning Zero To Hero – Hands-On With Python

Published 1/2024
MP4 | Video: h264, 1920×1080 | Audio: AAC, 44.1 KHz
Language: English | Size: 6.05 GB | Duration: 10h 56m

Learn Deep learning practically from scratch using Python

What you’ll learn
How to build artificial neural networks
Architectures of feedforward and convolutional networks
The calculus and code of gradient descent
Learn Python from scratch (no prior coding experience necessary)

Requirements
Basic Machine learning concepts and Python.

Description
Deep Learning is a new part of Machine Learning, which has been introduced with the objective of moving Machine Learning closer to Artificial Intelligence. Machine learning is a scientific discipline that explores the construction and study of algorithms that can learn from data. Such algorithms operate by building a model from example inputs and using that to make predictions or decisions, rather than following strictly static program instructions. Machine learning is closely related to and often overlaps with computational statistics; a discipline that also specializes in prediction-making. Through this training we are going to learn and apply concepts of deep learning with live projects.The course includes the following;•Prediction in Structured/Tabular Data•Recommendation•Image Classification•Image Segmentation•Object Detection•Style Transfer•Super Resolution•Sentiment Analysis•Text Generation•Time Series (Sequence) Prediction•Machine Translation•Speech Recognition•Question Answering•Text Similarity•Image Captioning•Image Generation•Image to Image TranslationWe will be learning the followings:The theory and math underlying deep learningHow to build artificial neural networksArchitectures of feedforward and convolutional networksBuilding models in PyTorchThe calculus and code of gradient descentFine-tuning deep network modelsLearn Python from scratch (no prior coding experience necessary)How and why autoencoders workHow to use transfer learningImproving model performance using regularization

Overview
Section 1: Deep Learning ZERO To HERO – Hands-On With Python

Lecture 1 Introduction to Hands on Deeplearning

Lecture 2 What is Machine Learning

Lecture 3 Popular ML Methods

Lecture 4 What is Deep Learning

Lecture 5 Applications of Deeplearning

Lecture 6 Recommendations

Lecture 7 Basic Concept of Deeplearning

Lecture 8 Perception

Lecture 9 Neural Network

Lecture 10 Universal Approximations Theorem

Lecture 11 Deep Neural Network

Lecture 12 Deep Neural Network Continue

Lecture 13 Getting Started

Lecture 14 Where to write Code

Lecture 15 Jupiter Notebook

Lecture 16 Google Colab

Lecture 17 Pytorch

Lecture 18 Tensors

Lecture 19 Tensors Continue

Lecture 20 Gradients

Lecture 21 MNIST Example

Lecture 22 Check Sample

Lecture 23 Hidden Layer

Lecture 24 Interface on a Digit

Lecture 25 Transfer-Learning-Overview

Lecture 26 What is Transfer Learning

Lecture 27 CS231n Convolutional Neural Networks

Lecture 28 Download Dataset

Lecture 29 Transform the Data

Lecture 30 Visualize the Data

Lecture 31 Define the Model

Lecture 32 Add a Few Final Layers

Lecture 33 Train the Model

Lecture 34 Test the Model

Lecture 35 What About CIFAR

Lecture 36 Image Classifier on Cifar 10 Dataset

Lecture 37 Download and Load Our Dataset

Lecture 38 Train and Test Dataset

Lecture 39 Define Our Neural Network

Lecture 40 Working on Image

Lecture 41 Input and Output

Lecture 42 Define Our Loss Function

Lecture 43 Train Data in Enumerate

Lecture 44 Train Data in Enumerate Continue

Lecture 45 Test the Neural Network on the Test Image

Lecture 46 Intro to Text Classifier

Lecture 47 Text Classification Using CNN

Lecture 48 Prepare the Data

Lecture 49 Build the Model

Lecture 50 Build the Model Coninue

Lecture 51 More on Build the Model

Lecture 52 Define a Loss Function

Lecture 53 Define a Loss Function Continue

Lecture 54 More on Define a Loss Function

Lecture 55 Evaluate or Test the Model

Lecture 56 Intro to Text Generation

Lecture 57 Text Generation-Transformers

Lecture 58 Text Generation-Transformers Continue

Lecture 59 Transformers-Architectures

Lecture 60 Transformers-Architectures Cintinue

Lecture 61 Word-Generation

Lecture 62 Word-Generation Continue

Lecture 63 Text-Generation

Lecture 64 Intro to Text Translation

Lecture 65 Loading-Data

Lecture 66 Preparing-Data

Lecture 67 Encoder-Attention Part 1

Lecture 68 Encoder-Attention Part 2

Lecture 69 Encoder-Attention Part 3

Lecture 70 Decoder

Lecture 71 Train-Eval-Functions

Lecture 72 Train-Eval-Functions Continue

Lecture 73 Training-Fixes

Lecture 74 Training-Evaluation

Lecture 75 Prediction-Tabular-Data Part 1

Lecture 76 Prediction-Tabular-Data Part 2

Lecture 77 Prediction-Tabular-Data Part 3

Lecture 78 Prediction-Tabular-Data Part 4

Lecture 79 Collaborative Filtering

Lecture 80 Collaborative Filtering Continue

Lecture 81 Other Recommendation Approaches

Aspiring Data Scientists and AI/Machine Learning/Deep Learning Engineers

Password/解压密码www.tbtos.com

转载请注明：0daytown » Deep Learning Zero To Hero – Hands-On With Python