As 2023 is dawning if you are deteremined to boost your career in AI, machine learning and deeplearning, I would like you to get headstart. Here is a list of courses that you should take up.

I would like to thank each one of 22,000 students in 145 countries for taking advantage of my courses on AI, Search and recommendations. My Instructor Profile is here

Semantic Search engine using Sentence BERT

Learn to build semantic search engine detection engine with sentence BERT

Build a strong foundation in Semantic Search with this tutorial for beginners.

  • Understanding of semantic search
  • Learn word embeddings from scratch
  • Learn limitation of BERT for sentences
  • Leverage sentence BERT for finding similar news headlines
  • Learn how to represent text as numeric vectors using sentence BERT embeddings
  • User Jupyter Notebook for programming
  • Build a real life web application or semantic search

A Powerful Skill at Your Fingertips  Learning the fundamentals of semantic search puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, has excellent documentation.

No prior knowledge of word embedding or BERT is assumed. I’ll be covering topics like Word Embeddings , BERT , Glove, SBERT from scratch.

Jobs in semantic search systems area are plentiful, and being able to learn it with BERT will give you a strong edge. BERT is  state of art language model and surpasses all prior techniques in natural language processing.

Semantic search is becoming very popular. Google, Yahoo, Bing and Youtube are few famous example of semantic search systems in action.  Semantic search engines are vital in information retrieval .  Learning semantic search with SBERT will help you become a natural language processing (NLP) developer which is in high demand.

Content and Overview  

This course teaches you on how to build semantic search engine using open source Python and Jupyter framework.  You will work along with me step by step to build following answers

  • Introduction to semantic search
  • Introduction to Word Embeddings
  • Build an jupyter notebook step by step using BERT
  • Build a real world web application to find similar news headlines

What am I going to get from this course?

  • Learn semantic search and build similarity search engine from professional trainer from your own desk.
  • Over 10 lectures teaching you how to build similarity search engine
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Ranking Search Results using Machine Learning

Learn ranking search results with the machine learning and popular programming language Python and Elastic Search.

Build a strong foundation in Machine Learning with this tutorial for intermediate programmers.

  • Understanding of Search Ranking
  • Leverage Machine Learning to rank search results
  • Use PyCharm and Python for programming
  • Use LAMBDAMART, LAMBDANET, RANKNET Machine Learning Algorithms for ranking Search results
  • Use RankLib to train ranking models
  • Use Learning To Rank Plug to configure and collect features

A Powerful Skill at Your Fingertips  Learning the fundamentals of ranking search results  puts a powerful and very useful tool at your fingertips. Python and Elastic Search are free, easy to learn, has excellent documentation.

Jobs in machine learning area are plentiful, and being able to learn ranking search results with machine learning will give you a strong edge.

Machine Learning is becoming very popular. Alexa, Siri, IBM Deep Blue and Watson are some famous example of Machine Learning application. Ranking search results is vital in information retrieval.  Learning ranking search results with machine learning will help you become a machine learning developer which is in high demand.

Big companies like Google, Bloomberg, Microsoft,  and  Yahoo already using ranking search results with machine learning in information retrieval and social platforms. They claimed that using Machine Learning and ranking search results has boosted productivity of entire company significantly.

Content and Overview  

This course teaches you on how to  rank search results using open source Python and Elastic Search framework.  You will work along with me step by step to build following answers

  • Introduction to Search Ranking
  • Introduction to Search Ranking using Machine Learning
  • Build an application step by step using Learning to Rank plug in, Elastic Search, Python and demo application from Open Source connections
  • Feature Engineering
  • Collect Features
  • Train Models
  • Evaluate Models
  • Learn use cases of ranking search results with machine learning

What am I going to get from this course?

  • Learn ranking search results and Machine Learning programming from professional trainer from your own desk.
  • Over 10 lectures teaching you ranking search results programming
  • Suitable for intermediate programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.

Generate photorealistic human faces using GAN

This course teaches you on how to build GAN using open source Tensorflow, Python, and Jupyter framework.  You will work along with me step by step to build following answers

  • Learn to generate synthetic yet photorealistic human faces using GAN
  • Build a strong foundation in GAN with this tutorial for intermediate developers.
  • Understanding of  GAN
  • Learn DCGAN and CNN from scratch
  • Learn Applications of GAN
  • Learn to code a Generator network using Tensorflow
  • Learn to code the Discriminator network using Tensorflow
  • Learn to code training of DCGAN model
  • User Jupyter Notebook for programming
  • Build a realistic photo generator using DCGAN

No prior knowledge of CNN or GAN is assumed. I’ll be covering topics like CNN, Generator, GAN, and DCGAN from scratch.

Jobs in the GAN area are plentiful, and being able to learn it with Python and Tensorflow will give you a strong edge. BERT is  state of art language model and surpasses all prior techniques in natural language processing.

GAN is becoming very popular. Google, Yahoo, Bing and Youtube are few famous examples of GAN systems in action.  GAN engines are vital in synthetic image generation.  Learning GAN with Tensorflow will help you become a Computer Vision Machine learning engineer which is in high demand.


Learn how to create content based hotel recommendations

This course teaches you how to build recommendation systems using open-source Python and Jupyter framework.  You will work along with me step by step to build the following answers.

  • Introduction to recommendation systems.
  • Introduction to Collaborative filtering
  • Build a jupyter notebook step by step using item-based collaborative filtering
  • Build a real-world web application to recommend music

Build movie review classification using BERT and Tensorflow

This course teaches you how to build a movie review classification engine using open-source Python, Tensorflow 2.4, and Jupyter framework.  You will work along with me step by step to build a movie review classification engine

  • Word Embeddings
  • Word2Vec
  • One hot encoding
  • Glove
  • BERT

  • Build Application
  • Download dataset
  • Download pre-trained model
  • Fine Tune Model on IMDB movie review dataset
  • Model Evaluation
  • Testing Model on real-world data

Toxic question classifier using BERT and Tensorflow 2.4

Learn to build Toxic Question Classifier  engine with BERT and TensorFlow 2.4

Build a strong foundation in Deep learning question classifiers with this tutorial for beginners.

  • Understanding of text classification
  • Learn word embeddings from scratch
  • Learn BERT and its advantages over other technologies
  • Leverage pre-trained model and fine-tune it for the questions classification task
  • Learn how to evaluate the model
  • User Jupyter Notebook for programming
  • Test model on real-world data

A Powerful Skill at Your Fingertips  Learning the fundamentals of text classification h puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, have excellent documentation. Text classification is a fundamental task in natural language processing (NLP) world.

No prior knowledge of word embedding or BERT is assumed. I’ll be covering topics like Word Embeddings, BERT, and Glove from scratch.

Jobs in the NLP area are plentiful, and being able to learn text classification with BERT will give you a strong edge. BERT is state of art language model and surpasses all prior techniques in natural language processing.

Google uses BERT for text classification systems. Text classifications are vital in social media.  Learning text classification with BERT and Tensorflow 2.4 will help you become a natural language processing (NLP) developer which is in high demand.


Build iOS mobile application for Question Answering with BERT embeddings

This course teaches you step by step on how tp build iOS question answering application. It explores the world of machine learning from application developer’s perspective. It explains the world of word embeddings which is fundamental technology behind text processing. As Andrew Ng has said “AI is new electricity”. The course highlight difference among AI (Artificial Intelligence, Machine learning and deep learning.  It also teaches few embedding technologies like glove, word2vec and BERT.

BERT is state of art transformer model developed by Google and has proven to be equivalent of CNN in computer vision technology. This course uses pretrained BERT model and explains how to use it in IOS question answering app.

The students once armed with this knowledge will be able to demonstrate their command  on machine learning and can use this technology for several different apps.

The author assumes that the student does not have any background in machine learning.

The course is structured as follows

  • App Preview : Shows preview of app that we are going to build
  • Embeddings : Explains what word embeddings are and why are they important
  • Deep Neural Network : It covers fundamentals of deep learning, and multi layer perceptron
  • BERT, Glove, Word2Vec : Popular word embedding technologies
  • Build UI from scratch :  Shows how to build UI by using basic controls in iOS swift
  • Step by Step Coding : Each function is explained in details with step by step walkthrough of the code
  • Text to Speech and Speech to text : This sections explains how to use test to speech and speech top text conversion libraries in iOS app so that user can speak question into the app and hear the answer . This is extremely useful for physically challenged users who can not type using keyboard *Run the app on iPhone : Shows the flow of the app on the phone.

Learn to build image classifier iOS mobile application

Learn to build Caltech-101 image classifier iPhone app using Apple’s crate ML and core ML SDK.  Deep learning is popular where a machine can be trained to detect objects in images.  Once trained, it can be used to detect objects in any image. The app does not require any wifi or cellular connectivity.  It uses deep learning to train the model from scratch on your own image dataset. The model can then be used inside an mobile app using Apple’s coreML SDK. We’ll build this app in this course. Since the app does not send your images or vides to remote service, it maintains your privacy and data secured.

Build a strong foundation in pose detection engines  with this tutorial for beginners.

  • Understanding fundamentals of CreateML and CoreML
  • Understanding fundamentals of deep learning and CNN 
  • Train a model on your own dataset using create ML SDK and XCode
  • Build a real life object detection mobile application  using coreml and swift
  • A Powerful Skill at Your Fingertips  Learning the fundamentals of object detection  puts a powerful and very useful tool at your fingertips. swift, create ml and coreml are free, easy to learn, has excellent documentation.
  • No prior knowledge of CNN or deep learning is assumed. I’ll be covering topics like CNN from scratch.

Jobs in computer vision area are plentiful, and being able to learn object detection will give you a strong edge. Learning object detection will help you become a computer vision developer which is in high demand.

Content and Overview  

This course teaches you on how to build object detection engine using open source create ml, coreml and swift .  You will work along with me step by step to build following answers

  • Train Object Detection model
  • Build Mobile object detection app using trained model

What am I going to get from this course?

  • Learn object detection from professional trainer from your own desk.
  • Over 10 lectures teaching you how to build  object detection engine
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Learn to build human pose detection iOS mobile application

Learn to build real time pose detection iPhone app using Posenet deep learning algorithm.  Deep learning is popular where a machine can be trained to detect poses in video and images.  Once trained, it can be used to detect poses in any video or image. The app does not require any wifi or cellular connectivity.  It uses deep learning and pretrained posenet model. It leverages apple’s coreml and vision SDK to achieve pose detection entirely on the phone. Since the app does not send your images or vides to remote service, it maintains your privacy and data secured.

Build a strong foundation in pose detection engines  with this tutorial for beginners.

  • Understanding fundamentals of pose detection
  • Understanding fundamentals of deep learning and CNN 
  • Benefits of posenet for fitness apps
  • Build a real life pose detection in video using posenet, computer vision, coreml and swift
  • Build a real life pose detection in image  using posenet, computer vision,, coreml and swift

A Powerful Skill at Your Fingertips  Learning the fundamentals of real time pose detection  puts a powerful and very useful tool at your fingertips. swift, posenet and coreml are free, easy to learn, has excellent documentation.

No prior knowledge of CNN or deep learning is assumed. I’ll be covering topics like CNN from scratch.

Jobs in computer vision area are plentiful, and being able to learn real time object detection will give you a strong edge. YOLO is  state of art technology that can quickly help you achieve your goal.

Learning pose detection with posenet will help you become a computer vision developer which is in high demand.

Content and Overview  

This course teaches you on how to build real time pose detection engine using open source posenet, coreml and swift .  You will work along with me step by step to build following answers

  • Real time pose detection in Video
  • Real time pose detection in image
  • Fundamentals of CNN and posenet

What am I going to get from this course?

  • Learn posenent and build real time pose detection engine from professional trainer from your own desk.
  • Over 15 lectures teaching you how to build real time pose detection engine
  • Suitable for intermediate programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Real time object detection in video using YOLO on iPhone

Learn to build real time object detection engine using YOLO deep learning algorithm.  Deep learning is popular where a machine can be trained to detect objects in video and images.  Once trained, it can be used to detect objects in any video or image.

Yolo (You only look Once) algorithm has become popular because of its real time nature. It can detect objects at 45 frames per second or within 20 ms. This makes it attractive to use it in self driving car where detecting objects in real time is key to avoid collisions. Unlike its predecessor, YOLO looks at image only once.

Build a strong foundation in image search engines  with this tutorial for beginners.

  • Understanding fundamentals of YOLO
  • Understanding fundamentals of deep learning and CNN 
  • Benefits of YOLO for self driving car use case
  • Build a real life object detection in video  using YOLO, coreml and swift
  • Build a real life object detection in image  using YOLO, coreml and swift
  • A Powerful Skill at Your Fingertips  Learning the fundamentals of real time object detection  puts a powerful and very useful tool at your fingertips. swift, YOLO and coreml are free, easy to learn, has excellent documentation.
  • No prior knowledge of CNN or deep learning is assumed. I’ll be covering topics like CNN from scratch.
  • Jobs in object detection area are plentiful, and being able to learn real time object detection will give you a strong edge. YOLO is  state of art technology that can quickly help you achieve your goal.
  • Learning object detection with YOLO will help you become a computer vision developer which is in high demand.

Content and Overview  

This course teaches you on how to build real time object detection engine using open source YOLO, OPNCV and Python .  You will work along with me step by step to build following answers

  • Real time object detection in Video
  • Real time object detection in image
  • Fundamentals of CNN and YOLO

What am I going to get from this course?

  • Learn YOLO and build real time object detection engine from professional trainer from your own desk.
  • Over 10 lectures teaching you how to build real time object detection engine
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Introduction to Convolutional Neural Network

Learn to build image classification engine with using Convolutional Neural Network (CNN) . CNN is popular network where a machine can be trained to classify images based on patterns in the images. Once trained, it can be used to identify objects in the images.

A lot of smart researchers have already spent lot of time building really good image classification networks like VGGNET, RESNET, Inception V3. The networks are variants of CNN. These networks have been trained on imagenet animal dataset. If your dataset requires a different type of image classification, you could just start with these networks and fine tune them on your smaller dataset. This saves significant time and resources.

Build a strong foundation in CNN with this tutorial for beginners.

  • Understanding fundamentals Convolution
  • Understanding fundamentals of deep learning and CNN
  • Benefits of CNN
  • Learn how to apply CNN with real example
  • Use Jupyter Notebook for step by step programming
  • Fine tune accuracy of CNN
  • Build a real life web application for dog vs cats classification

A Powerful Skill at Your Fingertips Learning the fundamentals of CNN puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, has excellent documentation.

No prior knowledge of CNN or deep learning is assumed. I’ll be covering topics like deep learning, Convolution and CNN from scratch.

Jobs in computer vision area are plentiful, and being able to learn transfer learning will give you a strong edge. CNN is state of art technology that can quickly help you achieve your goal.

Learning image classification with CNN will help you become a computer vision developer which is in high demand.

Content and Overview

This course teaches you on how to build dog vs cats classification engine using open source Python and Jupyter framework. You will work along with me step by step to build following answers

  • Introduction to Convolution
  • Introduction to CNN
  • Build an jupyter notebook step by step using CNN
  • Build a real world web application to find cat vs dog

What am I going to get from this course?

  • Learn CNN and build dog vs cats image classification engine from professional trainer from your own desk.
  • Over 10 lectures teaching you how to build image classification engine
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Building document scanner application using opencv (python)

Learn to scan documents by learning fundamentals of image scanning using opencv and popular programming language Python.

Build a strong foundation in document scanning with this tutorial for beginners.

  • Understanding of how document images are processed as array of RGB pixel intensities
  • Learn basics of document image scanning
  • Leverage OpenCV and Python to scan images of documents
  • User Jupyter Notebook for programming
  • Use step by step instructions along with plenty of examples
  • Build a real world application for single document and bulk document scanning

A Powerful Skill at Your Fingertips.  Learning the fundamentals of document scanning puts a powerful and very useful tool at your fingertips. Python, opencv and Jupyter are free, easy to learn, has excellent documentation.

Document scanning is important process to digitize information and save trees as it reduces paperwork. Jobs in image processing area are plentiful, and being able to learn opencv and python will give you a strong edge.

Content and Overview  

This course teaches you on how to scan receipts and books using opencv, python and Jupyter framework.  You will work along with me step by step to build following answers

  • Introduction to image processing
  • Learn how to apply scanning  to document images
  • Build an jupyter notebook step by step using opencv and python and learn effects like edge detection, perspective transform, contour drawing

What am I going to get from this course?

  • Learn fundamentals of image thresholding and build document scanning tasks from professional trainer from your own desk.
  • Over 10 lectures teaching you how to perform image thresholding using opencv and python
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Build a real world application for single document and bulk document scanning
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Fundamentals of image gradients and edge detection

Learn to process images by learning fundamentals of image gradients using opencv and popular programming language Python.

Build a strong foundation in Image Processing with this tutorial for beginners.

  • Understanding of how images are processed as array of RGB pixel intensities
  • Learn basics of image gradients
  • Leverage OpenCV and Python to detect edges using gradients
  • User Jupyter Notebook for programming
  • Use step by step instructions along with plenty of examples

A Powerful Skill at Your Fingertips  Learning the fundamentals of image thresholding puts a powerful and very useful tool at your fingertips. Python, opencv and Jupyter are free, easy to learn, has excellent documentation.

Image gradients is ubiquitous in everyday applications such as edge detection, medical diagnosis, license plate detection and image segmentation. Its also pre-requisite for computer vision applications using machine learning.

Jobs in image processing area are plentiful, and being able to learn opencv and python will give you a strong edge.

Image gradients tasks are becoming very popular. Amazon, Walmart, Google eCommerce websites are few famous example of image thresholding in action. Convolutional neural network (CNN) uses these techniques to detect boundaries of objects .

Image processing tasks are vital in information retrieval and computer vision applications . Big advertising companies and Hollywood studios already using image gradients in image segmentation

Content and Overview  

This course teaches you on how to smooth images using opencv, python and Jupyter framework.  You will work along with me step by step to build following answers

  • Introduction to image thresholding
  • Learn how to apply thresholding  to image
  • Build an jupyter notebook step by step using opencv and python and learn effects like bilateral thresholding, gaussian blur, median blur and average blur.

What am I going to get from this course?

  • Learn fundamentals of image thresholding and build image thresholding tasks from professional trainer from your own desk.
  • Over 10 lectures teaching you how to perform image thresholding using opencv and python
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

Building real world song recommendation engine with python

Course Description

Learn to build recommendation engine with Collaborative filtering and  popular programming language Python.

Build a strong foundation in Recommendation Systems with this tutorial for beginners.

  • Understanding of recommendation systems
  • Leverage Collaborative filtering to classify documents
  • User Jupyter Notebook for programming
  • Use singular value decomposition (SVD) for recommendation engine

A Powerful Skill at Your Fingertips  Learning the fundamentals of recommendation system puts a powerful and very useful tool at your fingertips. Python and Jupyter are free, easy to learn, has excellent documentation.

Jobs in recommendation systems area are plentiful, and being able to learn Collaborative filtering and SVD will give you a strong edge. Recommendation Systems ares becoming very popular. Amazon, Walmart, Google eCommerce websites are few famous example of recommendation systems in action. Recommendation Systems are vital in information retrieval, upselling and cross selling of products.  Learning Collaborative filtering with SVD will help you become a recommendation system developer which is in high demand.

Big companies like Google, Facebook, Microsoft, AirBnB and Linked In already using recommendation systens with item based collaborative in information retrieval and social platforms. They claimed that using recommendation systems has boosted productivity of entire company significantly.

Content and Overview :

This course teaches you on how to build recommendation systems using open source Python and Jupyter framework.  You will work along with me step by step to build following answers

  • Introduction to recommendation systems.
  • Introduction to Collaborative filtering
  • Build an jupyter notebook step by step using item based collaborative filtering
  • Build a real world web application to recommend music

What am I going to get from this course?

  • Learn recommendations systems and build real world music recommendation engine from professional trainer from your own desk.
  • Over 10 lectures teaching you how to build real world recommendation systems
  • Suitable for beginner programmers and ideal for users who learn faster when shown.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.
  • Offers challenges to students to enable reinforcement of concepts. Also solutions are described to validate the challenges.

A gentle introduction to deep neural networks

Learn intuition behind deep learning and artificial neural network (ANN)

Build a strong foundation in Machine Learning with this tutorial.

  • Understanding deep learning technology
  • Understand correlation between deep learning , machine learning and artificial intelligence
  • History of deep learning
  • Deep learning networks

A Powerful Skill at Your Fingertips  Learning the fundamentals of deep learning puts a powerful and very useful tool at your fingertips. Jobs in deep learning area are plentiful, and being able to learn deep learning  will give you a strong edge.

Deep learning is becoming very popular. Tesla self-driving cars, Alexa, Siri, IBM Deep Blue and Watson are some famous example of deep learning application. Understanding deep learning is vital in information retrieval, image classification and autonomous car driving.  

Big companies like Google, Facebook, Microsoft, AirBnB and Linked In already using deep learning in information retrieval, content ranking, image classification, autonomous car driving and ad targeting in social platforms. They claimed that using deep learning has boosted productivity of entire company significantly.

Content and Overview  

This course teaches you on how to build deep learning.  You will work along with me step by step to build intuition behind deep learning

  • Understanding deep learning technology
  • Understand correlation between deep learning , machine learning and artificial intelligence
  • History of deep learning
  • Learn neuron, perceptron
  • Learn feed forward network
  • Learn back propagation
  • Deep learning networks (CNN, R-CNN and LSTM)

What am I going to get from this course?

  • Learn deep learning from professional trainer from your own desk.
  • Over 10 lectures teaching you deep learning
  • Suitable for beginner programmers and ideal for executives who would like to learn intuition behind deep learning.
  • Visual training method, offering users increased retention and accelerated learning.
  • Breaks even the most complex applications down into simplistic steps.


<
Previous Post
Mobile phones have become a Single Point of Failures
>
Blog Archive
Archive of all previous blog posts