Course description
Artificial Intelligence Training in Bangalore
Who Should Attend:
Those who want to become master in Artificial intelligence And Natural Language Processing
Data Scientist/Analyst Who wants to improve their skills and want to learn Deep Learning/NLP
Freshers/Experienced Professional,Managers,IT professional
Prerequisite For Data Science Course:
You should be familiar with Python Programming and Machine learning to be eligible for this course.
Schedule Career Counselling Session
Duration Of Course – 10 Weeks Course (Weekend Only 3.5 Hours Saturday And Sunday) – 75 Hours Course
4 Months Duration
Course Fee: Rs. 55,000/- + Taxes
- Course Features:
- Online And Classroom data science training in Bangalore by industry experts
- Classes with 40% theory and 60% hands on
- Practical Approach With Mini Projects And Case studies.
- Job Assistance And Placement Support After end of Course.
Course Content
Download Course Brochure And Syllabus
|
PART A – Natural Language Procession(4 Weekends-20 Hours)
1. Introduction to NLP & Text Analytics Introduction to Text Analytics Introduction to NLP What is Natural Language Processing? What Can Developers Use NLP Algorithms For? NLP Libraries Need of Textual Analytics Applications of Natural Language Procession Word Frequency Algorithms for NLP Sentiment Analysis | 2. Text Pre Processing Techniques Need of Pre-Processing Various methods to Process the Text data Tokenization ,Challenges in Tokenization Stopping ,Stop Word Removal Stemming – Errors in Stemming Types of Stemming Algorithms – Table lookup Approach ,N-Gram Stemmers |
3. Distance Algorithms used in Text Analytics string Similarity Cosine Similarity Mechanishm – Similarity between Two text documents Levenshtein distance – measuring the difference between two sequences Applications of Levenshtein distance LCS(Longest Common Sequence ) Problems and solutions ,LCS Algorithms | 4. Information Retrieval Systems Information Retrieval – Precision,Recall,F-score TF-IDF KNN for document retrieval K-Means for document retrieval Clustering for document retrieval |
5. Topic Modelling & Dirchlett Distributions Introduction to Topic Modelling Latent Dirchlett Allocation Adavanced Text Analytics & NLP Introduction to Natural Language Toolkit POS Tagging NER | 6.5. Projects And Case Studies a. Sentiment analysis for twitter, web articlesb. Movie Review Predictionc. Summarization of Restaurant Reviews |
PART B-Deep Learning Using TensorFlow And Keras(6 Weekends – 35 hours )
1. Introduction to Deep Learning What is Deep Learning? Machine Learning VS Deep Learning Limitations Of Machine Learning Problems that Deep Learning Can Solve. Advantages of Deep Learning over Machine Learning | 2. Introduction to Tensor Flow Installing TensorFlow Simple Computation ,Contants And Variables Types of file formats in TensorFlow Creatting A Graph – Graph Visualization Creating a Model – Logistic Regression Model Building TensorFlow Classification Examples |
5. Recurrent Neural Networks (RNN) Introducing Recurrent Neural Networks skflow – RNNs in skflow Application use cases of RNN Manual Creation of RNN Long Short-Term memory (LSTM) And GRU theory Restricted Boltzmann Machine(RBM) And Autoencoders Collaborative Filtering with RBM Dimensionality Reduction with Linear Autoencoder | 4. Convolutional Neural Network(CNN) Convolutional Layer Motivation Convolutional Layer Application Architecture of a CNN Pooling Layer Application Deep CNN Understanding and Visualizing a CNN |
5. Recurrent Neural Networks (RNN) Introducing Recurrent Neural Networks skflow – RNNs in skflow Application use cases of RNN Manual Creation of RNN Long Short-Term memory (LSTM) And GRU theory Restricted Boltzmann Machine(RBM) And Autoencoders Collaborative Filtering with RBM Dimensionality Reduction with Linear Autoencoder | 6. Understanding Of TFLearn APIs Getting Started With TFLearn High-Level API usage -Layers, Built-in Operations,Training and Evaluatiion-Customizing the Training Process,Visualization APIs Sequential And Functional Composition Fine tuning, Using TensorBoard with TFLearn |
7. Understanding Of Keras APIs Understanding Keras API for implementing Neural Networks. Getting Strated With Keras APIs Keras Model ,Sequential And Functional Model,shared layers,Composig a Model with Keras API BAtch Normalization Tensor Board With Keras | Projects And Case Studiesa.Building a CNN for Image Classification b. SPAM Prediction Using RNN |
PART C – Computer Vision ( 3 Weekends – 20 hours )
1. Introduction to Computer Vision Introduction to computer Vision Computer Vision overview Historical Perspective | 2. Image Classification Data Driven approach K-nearest Neig |
3. OpenCv Library Opencv Installation And Python API Drawing shapes ,Image Processing Image Rotation and Thresholding Image Filtering – Gaussian Blur,Median Blur Feature Detection – Canny Edge Detector5. Convolutional Neural Network Activation Functions, Initialization Dropout, Update Rules | 4. Use of Neural Network in CV Multi-Layer Perceptron Backpropagation6. Object Detection(SSD) Single Shot MultiBox Detector, Object Localization How would you find an object in an image? The Problem of Scale and Shape SSD in TensorflowFace Detection 7. Project Using Computer vision And Deep Learning |
Certificates On successful Completion of Project And Assessment.
Tejas B – :
.