Rohan Shahane
Research Subjects
Rohan Shahane has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Nagarjuna Nellutla
Independent Researcher,Eagan,MN,USA,55123
1 shared publication - Nandita Giri
Independent Researcher,Seattle,WA,USA,98039
1 shared publication - Naveen Prakash Kandula
Independent Researcher,Atlanta,GA,USA,30028
1 shared publication - Nethaji Kapavarapu
Independent Researcher,Tallahassee,FL,USA,32311
1 shared publication - Ramesh Bellamkonda
Independent Researcher,Cumming,GA,USA,30040
1 shared publication - Sashi Kiran Kaata
Independent Researcher,Glendale,AZ,USA,85305
1 shared publication
Latest Publications
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
AutoPilot AI: Architecting Self-Healing ML Systems with Reinforcement Feedback Loops
In the fast-growing world of machine learning (ML), it is hard to maintain the model accuracy, stability, and operability over time in an unchanging environment, not to mention dynamic data. This paper presents AutoPilot AI, a new architectural framework that enables reinforcement feedback loops to build self-healing ML systems that perform autonomous adaptation and recovery. The considered approach utilizes reinforcement learning agents to supervise the model performance and concept drift detection and executes automated retraining or fine-tuning through soft-action, without waiting on continuous feedback of the environment. AutoPilot AI combines meta-learning and closed-loop control strategies to provide proactive anomaly mitigation, increase the amount of downtime reduction and minimize human influence. Scalable orchestration layers and XAI module further boost the framework, providing transparency and accountability. Real-world testing using real-life data proves that the framework could produce good model fidelity and several years of operational resilience. This paper is a real milestone to achieving fully autonomous, self-optimizing real-time, mission-critical application ML pipelines.
- 29 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
AutoPilot AI: Architecting Self-Healing ML Systems with Reinforcement Feedback Loops
In the fast-growing world of machine learning (ML), it is hard to maintain the model accuracy, stability, and operability over time in an unchanging environment, not to mention dynamic data. This paper presents AutoPilot AI, a new architectural framework that enables reinforcement feedback loops to build self-healing ML systems that perform autonomous adaptation and recovery. The considered approach utilizes reinforcement learning agents to supervise the model performance and concept drift detection and executes automated retraining or fine-tuning through soft-action, without waiting on continuous feedback of the environment. AutoPilot AI combines meta-learning and closed-loop control strategies to provide proactive anomaly mitigation, increase the amount of downtime reduction and minimize human influence. Scalable orchestration layers and XAI module further boost the framework, providing transparency and accountability. Real-world testing using real-life data proves that the framework could produce good model fidelity and several years of operational resilience. This paper is a real milestone to achieving fully autonomous, self-optimizing real-time, mission-critical application ML pipelines.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Training AI to Simulate Reality Through Self-Constructed Representations
Generating correct and flexible models of realistic, partially unknown worlds is an old goal in artificial intelligence. Developments in representation learning, generative modelling, inventions of self-supervised methods mean that AI systems have attained inner models of the world that allow them to perform nearly the same as human perception regarding real-world dynamics without direct supervision. In this paper, an innovative training scheme to train AI agents to anticipate a reality by learning self-built portrayal of their environment is covered. Using variational autoencoders and generative adversarial networks, our method allows agents to learn underlying structure and predict future states and in addition to being able to represent a large number of complex realistic scenarios. We experimentally analyse the efficacy of this approach in the domains of synthetic and physical preparations that reinforce the realization of agents outfitted with self-built world models giving better generalization, predictive precision, and utilization of resources. With references to experimental results, the models are likely to contribute to increasing real-time decision making, autonomous control as well as creation of virtual environment in a wide selection of practical applications. Lastly, we mention some of the main limitations such as representation fidelity, scalability, and computational complexity and future directions depending on which simulations could be made to use better representations and achieve results that could be deployed in dynamic real-world environments more easily.
- 4 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Training AI to Simulate Reality Through Self-Constructed Representations
Generating correct and flexible models of realistic, partially unknown worlds is an old goal in artificial intelligence. Developments in representation learning, generative modelling, inventions of self-supervised methods mean that AI systems have attained inner models of the world that allow them to perform nearly the same as human perception regarding real-world dynamics without direct supervision. In this paper, an innovative training scheme to train AI agents to anticipate a reality by learning self-built portrayal of their environment is covered. Using variational autoencoders and generative adversarial networks, our method allows agents to learn underlying structure and predict future states and in addition to being able to represent a large number of complex realistic scenarios. We experimentally analyse the efficacy of this approach in the domains of synthetic and physical preparations that reinforce the realization of agents outfitted with self-built world models giving better generalization, predictive precision, and utilization of resources. With references to experimental results, the models are likely to contribute to increasing real-time decision making, autonomous control as well as creation of virtual environment in a wide selection of practical applications. Lastly, we mention some of the main limitations such as representation fidelity, scalability, and computational complexity and future directions depending on which simulations could be made to use better representations and achieve results that could be deployed in dynamic real-world environments more easily.