Deep Learning Nlp For Sentiment Analysis & Translation 2023

Published 2/2023MP4 | Video: h264, 1280x720 | Audio: AAC, 44.1 KHzLanguage: English | Size: 9.16 GB | Duration: 20h 36m

Master and Deploy Sennt analysis and machine translation solutions with Tensorflow and Hugggingface Transformers

What you'll learn

The Basics of Tensors and Variables with Tensorflow

Linear Regression, Logistic Regression and Neural Networks built from scratch.

Basics of Tensorflow and training neural networks with TensorFlow 2.

Model deployment

Conversion from tensorflow to Onnx Model

Quantization Aware training

Building API with Fastapi

Deploying API to the Cloud

Sennt Analysis with Recurrent neural networks, Attention Models and Transformers from scratch

Neural Machine Translation with Recurrent neural networks, Attention Models and Transformers from scratch

Neural Machine Translation with T5 in Huggingface transformers

Attention Networks

Transformers from scratch

Requirements

Basic Math

Access to an internet connection, as we shall be using Google Colab (free version)

Basic Knowledge of Python

Description

Sennt analysis and machine translation models are used by millions of people every single day. These deep learning models (most notably transformers) power different industries today. With the creation of much more efficient deep learning models, from the early 2010s, we have seen a great improvement in the state of the art in the domains of sennt analysis and machine translation.In this course, we shall take you on an amazing journey in which you'll master different concepts with a step-by-step approach. We shall start by understanding how to process text in the context of natural language processing, then we would dive into building our own models and deploying them to the cloud while observing best practices. We are going to be using Tensorflow 2 (the world's most popular library for deep learning, built by Google) and HuggingfaceYou will learn:The Basics of Tensorflow (Tensors, Model building, training, and evaluation).Deep Learning algorithms like Recurrent Neural Networks, Attention Models, Transformers, and Convolutional neural networks.Sennt analysis with RNNs, Transformers, and Huggingface Transformers (Deberta)Transfer learning with Word2vec and modern Transformers (GPT, Bert, ULmfit, Deberta, T5...)Machine translation with RNNs, attention, transformers, and Huggingface Transformers (T5)Model Deployment (Onnx format, Quantization, Fastapi, Heroku Cloud)If you are willing to move a step further in your career, this course is destined for you and we are super excited to help achieve your goals!This course is offered to you by Neuralearn. And just like every other course by Neuralearn, we lay much emphasis on feedback. Your reviews and questions in the forum will help us better this course. Feel free to ask as many questions as possible on the forum. We do our very best to reply in the shortest possible .Enjoy!!!

Overview

Section 1: Introduction

Lecture 1 Welcome

Lecture 2 General intro

Section 2: Tensors and variables

Lecture 3 Basics

Lecture 4 Initialization and Casting

Lecture 5 Indexing

Lecture 6 Maths Operations

Lecture 7 Linear algebra operations

Lecture 8 Common methods

Lecture 9 Ragged tensors

Lecture 10 Sparse tensors

Lecture 11 String tensors

Lecture 12 Variables

Section 3:[PRE-REQUISCITE] Building neural networks with tensorflow

Lecture 13 Task understanding

Lecture 14 Data preparation

Lecture 15 Linear regression model

Lecture 16 Error sanctioning

Lecture 17 Training and optimization

Lecture 18 Performance measurement

Lecture 19 Validation and testing

Lecture 20 Corrective measures

Section 4: Text Preprocessing for Sennt Analysis

Lecture 21 Understanding Sennt Analysis

Lecture 22 Text Standardization

Lecture 23 Tokenization

Lecture 24 One-hot encoding and Bag of Words

Lecture 25 Term frequency - Inverse Document frequency (TF-IDF)

Lecture 26 Embeddings

Section 5: Sennt Analysis with Recurrent neural networks

Lecture 27 How Recurrent neural networks work

Lecture 28 Data preparation

Lecture 29 Building and training RNNs

Lecture 30 Advanced RNNs (LSTM and GRU)

Lecture 31 1D Convolutional Neural Network

Section 6: Sennt Analysis with transfer learning

Lecture 32 Understanding Word2vec

Lecture 33 Integrating pretrained Word2vec embeddings

Lecture 34 Testing

Lecture 35 Visualizing embeddings

Section 7: Neural Machine Translation with Recurrent Neural Networks

Lecture 36 Understanding Machine Translation

Lecture 37 Data Preparation

Lecture 38 Building, training and testing Model

Lecture 39 Understanding BLEU score

Lecture 40 Coding BLEU score from scratch

Section 8: Neural Machine Translation with Attention

Lecture 41 Understanding Bahdanau Attention

Lecture 42 Building, training and testing Bahdanau Attention

Section 9: Neural Machine Translation with Transformers

Lecture 43 Understanding Transformer Networks

Lecture 44 Building, training and testing Transformers

Lecture 45 Building Transformers with Custom Attention Layer

Lecture 46 Visualizing Attention scores

Section 10: Sennt Analysis with Transformers

Lecture 47 Sennt analysis with Transformer encoder

Lecture 48 Sennt analysis with LSH Attention

Section 11: Transfer Learning and Generalized Language Models

Lecture 49 Understanding Transfer Learning

Lecture 50 Ulmfit

Lecture 51 Gpt

Lecture 52 Bert

Lecture 53 Albert

Lecture 54 Gpt2

Lecture 55 Roberta

Lecture 56 T5

Section 12: Sennt Analysis with Deberta in Huggingface transformers

Lecture 57 Data Preparation

Lecture 58 Building,training and testing model

Section 13: Neural Machine Translation with T5 in Huggingface transformers

Lecture 59 Dataset Preparation

Lecture 60 Building,training and testing model

Bner Python Developers curious about Applying Deep Learning for Natural Language Processing in the domains of sennt analysis and machine translation,Deep Learning for NLP Practitioners who want gain a mastery of how things work under the hood,NLP practitioners who want to learn how state of art sennt analysis and machine translation models are built and trained using deep learning.,Anyone wanting to deploy ML Models,Learners who want a practical approach to Deep learning for Sennt analysis and Machine Translation

HomePage:

https://www.udemy.com/course/deep-learning-nlp-for-sennt-analysis-translation-2023/