AI Tutorial

Transfer Learning Basic Concept and the Building Blocks

Transfer Learning A Step by Step Easy Guide

In this tutorial you will learn the essence of Transfer Learning.  Python tensorflow keras are used for developing the deep learning frameworks of transfer learning. 

Transfer learning for deep machine learning is the process of first training a base network on a benchmark dataset (like ImageNet), and then transferring the best-learned network features (the network’s weights and structures) to a second network to be trained on a target dataset.

This idea has been shown to improve deep neural network’s generalization capabilities significantly in many application areas. Recently, considering the lengthening timelines for deep machine learning the interest in transfer learning has grown significantly.

What is Transfer Learning?

Transfer learning is currently used in almost every deep learning model when the target dataset does not contain enough labeled data. Building deep learning models from scratch and training with huge data is very expensive, both in time and resources. Transfer learning is very effective for rapid prototyping, resource efficiency and high performance. As human brain carry forward knowledge and wisdom and learn it from others, transfer learning mimic this type behavior.   

Transfer Learning Base Models

To design an efficient neural network model, you need to know the details of different base models. Because from the base model you will be transferring the knowledge to your new model.… Read more..

Key Artificial Intelligence Projects to Fight Against COVID-19https://amitray.com/artificial-intelligence-to-fight-against-covid-19/

Artificial Intelligence to Fight Against COVID-19

Key Artificial Intelligence Projects to Fight Against COVID-19

Dr. Amit Ray 
Compassionate  AI Lab 

Prevention and early healing are the primary requirements for the present COVID crisis. In our Compassionate AI Lab, we broadly classified our fight against COVID 19 Artificial intelligence (AI) based research projects into six groups. They are AI for COVID vaccine development, AI for COVID drug discovery, AI for COVID diagnosis, AI for COVID testing, AI for COVID growth rate forecasting, and AI for social robots.

AI to Fight COVID 19 Researches Sri Amit Ray Compassionate AI Lab

AI to Fight COVID 19 Researches Sri Amit Ray Compassionate AI Lab

Read More »Artificial Intelligence to Fight Against COVID-19

Top 10 Limitations of Deep Learning

Top 10 Limitations of Artificial Intelligence and Deep Learning

Artificial Intelligence (AI) has provided remarkable capabilities and advances in image understanding, voice recognition, face recognition, pattern recognition, natural language processing, game planning, military applications, financial modeling, language translation, and search engine optimization. In medicine, deep learning is now one of the most powerful and promising tool of AI, which can enhance every stage of patient care —from research, omics data integration, combating antibiotic resistance bacteria,  drug design and discovery to diagnosis and selection of appropriate therapy. It is also the key technology behind self-driving car.

However, deep learning algorithms of AI have several inbuilt limitations. To utilize the full power of artificial intelligence, we need to know its strength and weakness and the ways to overcome those limitations in near future.

Now, AI support messaging apps, and voice controlled chatbots are helping people for deep space communications, customer care, taking off the burden on medical professionals regarding easily diagnosable health concerns or quickly solvable health management issues and many other applications. However, there are many obstacles and number of issues remain unsolved. 

Even with so many success and promising results its full application is limited. Mainly, because, present day AI has no common sense about the world and the human psychology. Presently, in complex application areas, one part is solved by the AI system and the other part is solved by human – often called as human-assisted AI system.  The challenges are mostly in the large-scale application areas like drug discovery, multi-omics-data integration, assisting elderly people,  new material design and modeling,  computational chemistry, quantum simulation, and aerospace physics.

This article is focused to explain the power and challenges of current AI technologies and learning algorithms. It also provides the directions and lights to overcome the limits of AI technologies to achieve higher levels learning capabilities.

Top 10 Limitations of Artificial Intelligence and Deep LearningRead More »Top 10 Limitations of Artificial Intelligence and Deep Learning

Requirements for Quantum Computing

7 Key Requirements for Quantum Computing

Here, we discussed seven key  requirements for implementing efficient quantum computing systems. The seven key requirements are long coherence time, high scalability, high fault tolerance, ability to initialize qubits, universal quantum gatesefficient qubit state measurement capability, and faithful transmission of flying qubits.  They are seven guidelines for designing effective quantum computing systems. 

Quantum computing is the key technology for future artificial intelligence. In our Compassionate AI Lab, we are using AI based quantum computing algorithms for human emotion analysis, simulating human homeostasis with quantum reinforcement learning and other quantum compassionate AI projects.   This tutorial is for the researchers, volunteers and students of the Compassionate AI Lab for understanding the deeper aspects of quantum computing for implementing compassionate artificial intelligence projects. 

Earlier we have discussed Spin-orbit Coupling Qubits for Quantum Computing and AI Quantum Computing Algorithms for Artificial IntelligenceQuantum Computing and Artificial Intelligence and Quantum Computer with Superconductivity at Room Temperature. Here, we will focus on the exact requirements for developing efficient quantum computers. 

Building a quantum computer differs greatly from building a classical computer. The core of quantum computing is qubits.  Qubits are made using single photons, trapped ions, and atoms in high finesse cavities. Superconducting materials and  semiconductor quantum dots are promising hosts for qubits to build a quantum processor. When superconducting materials are cooled, they can carry a current with zero electrical resistance without losing any energy. These seven requirements refereed as DiVincenzo criteria for quantum computing [1]. 

Requirements for Quantum ComputingRead More »7 Key Requirements for Quantum Computing

AI for Balance-Control Fall Detection of Elderly People

Artificial Intelligence for Balance Control and Fall Detection of Elderly People

Balance control in elderly people is one of the key issues of old age. Artificial Intelligence can play a big role to solve this issue. In this research work, we demonstrate the application of machine learning techniques for posture alignments and the control of the body center of mass for disable people.

Designing automated balance control system for elderly people is one of the key project  of our Compassionate AI Lab. Here, Dr. Amit Ray discuses about one of the recent project of AI using deep learning algorithms for automatic balance control of elderly people. He explains how machine learning algorithms can be used to study and improve the dynamical properties of postural stability of elderly people. The project focuses on how image recognition, human-body joint dynamics, and path navigation methods of artificial intelligence can be used  to eliminate the imbalance, fall and injury of elderly people or for physically challenged people.

AI for Balance-Control Fall Detection of Elderly People

Compassionate Artificial Intelligence can be used for helping elderly people in many ways. Here, we discuss about one of our recent project of using AI & deep learning techniques for automatic balance control. The machine learning algorithms are used to improve dynamical properties of postural stability. In this project AI based machine learning algorithms are used to find the insights into the person specific postural strategies for older adults in order to adapt to the postural challenges during sleeping, standing, turning and walking. To study the body movement behavior of elderly people accurately, it is necessary to observe and record their movement trajectory and joint movements quantitatively and precisely in three dimensions.Read More »Artificial Intelligence for Balance Control and Fall Detection of Elderly People

Quantum Computer with Superconductivity at Room Temperature

Quantum Computer with Superconductivity at Room Temperature

Quantum computer with superconductivity at room temperature is going to change the landscape of artificial intelligence. In the earlier article we have discussed quantum computing algorithms for artificial intelligence.  In this article we reviewed the implication of superconductivity at room temperature on quantum computation and its impact on artificial intelligence.   

Long coherence time (synchronized), low error rate and high scalability are the three prime requirements for quantum computing.  To overcome these problems, presently, quantum computer needs complex infrastructure involving high-cooling and ultra-high vacuum. This is to keep atomic movement close to zero and contain the entangled particles, both of which reduce the likelihood of decoherence. The availability of superconductivity at room temperature will provide the quantum jump in quantum computer. 

Quantum Computer with Superconductivity at Room Temperature

Read More »Quantum Computer with Superconductivity at Room Temperature

Quantum Computing Algorithms for Artificial Intelligence

Quantum Computing Algorithms for Artificial Intelligence

Dr. Amit Ray explains the quantum annealing, Quantum Monte Carlo Tree Search, Quantum algorithms for traveling salesman problems, and Quantum algorithms  for gradient descent problems in depth.

This tutorial is for the researchers, developers, students and the volunteers of the quantum computing team of the  Sri Amit Ray Compassionate AI Lab. Many of our researchers and students asked me to explain the quantum computing algorithms in a very simplistic term.  The purpose of this article is to explain that.

Quantum Computing Algorithms for AI By Amit Ray

Earlier we have discussed Spin-orbit Coupling Qubits for Quantum Computing and the foundations of  Quantum computing and artificial intelligence.  This article is to explain the foundation quantum computing algorithms in depth in a simplistic way. Here we explained the concepts of quantum annealing, Quantum Monte Carlo Tree Search, quantum algorithms for traveling salesman problem and Quantum algorithms for gradient descent problems. Read More »Quantum Computing Algorithms for Artificial Intelligence

Spin-orbit Coupling Qubits for Quantum Computing

Spin-orbit Coupling Qubits for Quantum Computing and AI

The Power of Spin-orbit Coupling Qubits for Quantum Computing

Here, Dr. Amit Ray discusses the power, scope, and challenges of Spin-orbit Coupling Qubits for Quantum Computing with Artificial Intelligence in details. Quantum computing for artificial intelligence is one of the key research project of Compassionate AI Lab. We summarize here some of the recent developments on qubits and spin–orbit coupling  for quantum computing. 

In digital computing, information is processed as ones and zeros, binary digits (or bits). The analogue to these in quantum computing are known as qubits. The qubits are implemented in nanoscale dimensions, such as spintronic, single-electron devices and ultra-cold gas of Bose-Einstein condensate state devices. Manipulation and measurement of the dynamics of the quantum states before decoherence are the primary characteristic of quantum computing. 

 

Quantum Computing with AI

Involving electron spin  in designing electronic devices with new functionalities, and achieving quantum computing with electron spins is among the most ambitious goals of  compassionate artificial superintelligence – AI 5.0.  Utilizing quantum effects like quantum superposition, entanglement, and quantum tunneling for computation is becoming an emerging research field of quantum computing based artificial intelligence. 

Read More »Spin-orbit Coupling Qubits for Quantum Computing and AI

Deep Learning Research Datasets

List of Datasets for Artificial Intelligence, Data Science, Deep Learning and Machine Learning Projects.

This list is created for the research and experimentation of  compassionate AI Lab. 

  • UCI Machine Learning Repository, maintains 436 data sets as a service to the machine learning community.
  • MNIST – MNIST contains images for handwritten digit classification. It’s considered a great entry dataset for deep learning because it’s complex enough to warrant neural networks, while still being manageable on a single CPU. (We also have a tutorial.)
  • CIFAR – The next step up in difficulty is the CIFAR-10 dataset, which contains 60,000 images broken into 10 different classes. For a bigger challenge, you can try the CIFAR-100 dataset, which has 100 different classes.
  • ImageNet – ImageNet hosts a computer vision competition every year, and many consider it to be the benchmark for modern performance. The current image dataset has 1000 different classes.
  • YouTube 8M – Ready to tackle videos, but can’t spare terabytes of storage? This dataset contains millions of YouTube video ID’s and billions of audio and visual features that were pre-extracted using the latest deep learning models.
  • Kaggle Datasets – Open datasets contributed by the Kaggle community. Here, you’ll find a grab bag of topics.
Read more..