Deep Learning With Computer Vision and Advanced NLP

Deep Learning With Computer Vision and Advanced NLP

Start Date: 17th April 2021
Class Timings: 12:30 PM IST to 2:30 PM (IST) Saturday - Sunday
Doubt Clearing Session: 08:00 PM to 10:00 PM (IST) Thursday

Course Overview

Deep Learning With Computer Vision and Advanced NLP

What you'll learn
  • Advance NLP with deep-learning overview.
  • TensorFlow Installation.
  • Pytorch.
  • Neural Network.
  • CNN overview
  • Advance Computer Vision – Part 1.
  • Advance computer Vision – Part 2.
  • ChatBot.
  • Text processing
  • Spacy.
  • NLP terminalogy.
  • RNN
  • Attention Based model.
  • Hardware Setup – GPU.
  • Transfer Learning in NLP.
  • Mini NLP Project.
  • Deployment of Model and Performance tuning.
  • NLP Transfer learning project with deployment and integration with UI.
  • NLP end to end project with architecture and deployment.
  • NLP project end to end with deployment in various cloud and UI integration.
  • Computer Vision Project.
Requirements
  • Dedication
  • Computer with i3 processor and internet

Course Curriculum

  • Computational Linguistic
  • History of NLP
  • Why NLP
  • Use of NLP
  • Tensorflow Installation 2.0
  • Tensorflow Installation 1.6 with virtual environment
  • TensorFlow 2.0 function
  • Tensorflow 2.0 neural network creation
  • Tensorflow 1.6 functions
  • Tensorflow 1.6 neural network and its functions
  • Keras Introduction
  • Keras in-depth with neural network creation
  • Mini project in Tensorflow
  • Pytorch installation
  • Pyrotorch functional overview
  • Pytorch neural network creation
  • A Simple Perception
  • Neural Network overview and its use case
  • Various Neural Network architect overview
  • Use case of Neural Network in NLP and computer vision
  • Multilayer Network
  • Loss Functions
  • The Learning Mechanism
  • Optimizers
  • Forward and Backward Propagation
  • Gradient Descent
  • CNN definition and various CNN based architecture
  • End to End CNN network training
  • Deployment in Azure
  • Cloud performance tuning of CNN network
  • GAN
  • Generative Model Using GAN
  • BERT
  • Semi-Supervised learning using GAN
  • Restricted Boltzmann Machine (RBM) and Autocoders
  • CNN Architectures
  • LeNet-5
  • AlexNet
  • GoogleNet
  • VGGNet
  • ResNet
  • SSD
  • SSD lite
  • Faster R CNN
  • SCNN
  • Masked R-CNN
  • Xception
  • SENet
  • Facenet
  • Implementing a ResNet – 34 CNN using Keras
  • Pretrained Models from Keras
  • Pretrained Models for Transfer Learning
  • Intents and Entities
  • Fulfillment and integration
  • Chatbot using Microsoft bot builder and LUIS, development to Telegram, Skype
  • Chatbot using Microsoft bot builder and LUIS, development to Telegram, Skype
  • Chatbot using Amazon Lex, deployment to Telegram, Skype
  • Chatbot using RASA NLU, deployment to Telegram , Skype
  • Semantic Segmentation
  • Classification and Localisation
  • TensorFlow Object Detection
  • You Only Look Once (YOLO)
  • Importing Text
  • Web Scrapping
  • Text Processing
  • Understanding Regex
  • Text Normalisation
  • Word Count
  • Frequency Distribution
  • Text Annotation
  • Use of Anotator
  • String Tokenization
  • Annonator Creation
  • Sentence processing
  • Lemmatization in text processing
  • POS
  • Named Entity Recognition
  • Dependency Parsing in text
  • Sentimental Analysis
  • Spacy Overview
  • Spacy function
  • Spacy function implementation in text processing
  • POS tagging, challenges and acuracy
  • Entities and named entry Recognition, interpolation, Language models
  • Morphology and Diversity
  • Ambiguity and Paradigms
  • Structures and meanings
  • Lexical Knowledge, NetworknMetaphors and co-refrences
  • Lexical Ambiguity
  • Polysemy and homonymy
  • Conference Resolution
  • Anaphora and cataphora resolution
  • Multi-sentiential resolution
  • Humans and Ambiguity
  • Machines and ambiguity
  • Co-occurrence and distributional similarity
  • Similarity and relatedness
  • Knowledge graphs and repositories
  • Computational Linguistics
  • Word embeddings and co-occurrence vectors
  • Word Sim353 Dataset examples
  • Word2vec
  • Part of speech tagging
  • Recurrent Neural Networks
  • Long Short Term Memory (LSTM)
  • Bi LSTM
  • GRU implementation
  • Building a Story writer using character level RNN
  • Seq 2 Seq
  • Encoders and Decoders
  • Attention Mechanism
  • Attention Neural Networks
  • Self Attention
  • GPU Introduction
  • Various type of GPU configuration
  • GPU provider and its pricing
  • Paperspace GPU setup
  • Running model in GPU
  • Introdution to transformers
  • BERT Model
  • ELMo Model
  • GPT1 Model.
  • GPT2 Model
  • ALBERT Model
  • DistilBERT Model

Course Projects

  • Topic Modeling
  • Word sense disambiguation
  • Text to speech
  • Keyword Spotting
  • Document Ranking
  • Text Search (with Synonyms)
  • Language Modeling
  • Spam Detector
  • Image Captioning
  • Machine Translation
  • Abstractive text summarization
  • Keyword spotting
  • Language modelling
  • Document summarization
  • Deep learning model deployment strategies
  • Deep learning project architecture
  • Deep learning model deployment phase
  • Deep learning model retraining phase
  • Deep learning model deployment in aws
  • Deep learning model deployment in azure
  • Deep learning model deployment in gcloud
  • Deployment and integration with ui machine translation
  • Question answering (like chat – bot)
  • Sentiment analysis imdb
  • Text search (with synonyms)
  • Text classifications
  • Spelling corrector
  • Entity (person, place or brand) recognition
  • Text summarization
  • Text similarity (paraphrase)
  • Topic detection
  • Language identification
  • Document ranking
  • Fake news detection
  • Plagiarism checker
  • Text summarization extractive
  • Text summarization abstractive
  • Movie review using bert
  • Ner using bert
  • Pos bert
  • Text generation gpt 2
  • Text summarization xlnet
  • Abstract bert
  • Machine Translation
  • Nlp text summarization custom
  • Keras/tensorflow
  • Language identification
  • Text classification using fast bert
  • Neuralcore
  • Detecting fake text using gltr with bert and gpt2
  • Fake news detector using gpt2
  • Python plagiarism checker type a message
  • Question answering
  • Traffic Surveillance System
  • Object identification
  • Object tracking
  • Object classification
  • Tensorflow object detection
  • Image to text processing
  • Speech to speech analysis
  • Vision based attendance system
5.00 out of 5.0
1 Star 0.0%
2 Star 0.0%
3 Star 0.0%
4 Star 0.0%
5 Star 100.0%
Sudhanshu Kumar

Having 7+ years of experience in Big data, Data Science and Analytics with product architecture design and delivery. Worked in various product and service based Company. Having an experience of 5+ years in educating people and helping them to make a career transition.

Reviews

arpita gupta
July 30,2021
5.00

" I took deep learning, computer vision, and natural language processing course at Ineuron. The contents covered were excellent and the way of teaching by Sudhanshu sir. "

Chetan Hirapara
July 26,2021
5.00

" This is one of the best course, instructors has a very depth knowledge of each topics which are covered in this course. Thanks iNeuron team for this awesome course. "

Faizan Khan
June 25,2021
5.00

" The course content is amazing and the instructors are also very kind here. Definitely, the course is worth to buy. "

Submit Reviews

You can not rate this course before login

Join Thousand of Happy Students!

Subscribe our newsletter & get latest news and updation!