Aniruddha Mukherjee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Aniruddha Mukherjee has a total of 18 co-authors. Here are the top co-authors by number of shared publications:
- Vinay Chamola
BITS Pilani
3 shared publications - Vikas Hassija
School of Computer Engineering, KIIT, Bhubaneswar, India
2 shared publications - Abiy Abinet Mamo
School of Computer Engineering KIIT, Bhubaneshwar, India
1 shared publication - Aditya Gopalan
Indian Institute of Science Bangalore India
1 shared publication - Bealu Girma Gebresilassie
School of Computer Engineering KIIT, Bhubaneshwar, India
1 shared publication - Gal Dalal
NVIDIA Research
1 shared publication
Latest Publications
- Open Access
Reliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classical control tasks -- CartPole and Inverted Pendulum -- under changes to neural network and environmental parameters. Relative to DQN, Double DQN, DDPG, TD3, and PPO, RPI reaches near-optimal performance early and sustains this policy as training proceeds. Because deep RL methods are often hampered by sample inefficiency, training instability, and hyperparameter sensitivity, our results highlight RPI's promise as a more reliable alternative.
Open AccessReliable Policy Iteration: Performance Robustness Across Architecture and Environment Perturbations
In a recent work, we proposed Reliable Policy Iteration (RPI), that restores policy iteration's monotonicity-of-value-estimates property to the function approximation setting. Here, we assess the robustness of RPI's empirical performance on two classical control tasks -- CartPole and Inverted Pendulum -- under changes to neural network and environmental parameters. Relative to DQN, Double DQN, DDPG, TD3, and PPO, RPI reaches near-optimal performance early and sustains this policy as training proceeds. Because deep RL methods are often hampered by sample inefficiency, training instability, and hyperparameter sensitivity, our results highlight RPI's promise as a more reliable alternative.
- Open Access
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 6, 658-668
A Detailed Comparative Analysis of Automatic Neural Metrics for Machine Translation: BLEURT & BERTScore
Bleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.
- 14 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Computer Society
- Vol. 6, 658-668
Open AccessA Detailed Comparative Analysis of Automatic Neural Metrics for Machine Translation: BLEURT & BERTScore
Bleurt a recently introduced metric that employs Bert, a potent pre-trained language model to assess how well candidate translations compare to a reference translation in the context of machine translation outputs. While traditional metrics like Bleu rely on lexical similarities, Bleurt leverages Bert's semantic and syntactic capabilities to provide more robust evaluation through complex text representations. However, studies have shown that Bert, despite its impressive performance in natural language processing tasks can sometimes deviate from human judgment, particularly in specific syntactic and semantic scenarios. Through systematic experimental analysis at the word level, including categorization of errors such as lexical mismatches, untranslated terms, and structural inconsistencies, we investigate how Bleurt handles various translation challenges. Our study addresses three central questions: What are the strengths and weaknesses of Bleurt, how do they align with Bert's known limitations, and how does it compare with the similar automatic neural metric for machine translation, BERTScore? Using manually annotated datasets that emphasize different error types and linguistic phenomena, we find that Bleurt excels at identifying nuanced differences between sentences with high overlap, an area where BERTScore shows limitations. Our systematic experiments, provide insights for their effective application in machine translation evaluation.
- Open Access
Convolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture
This study demonstrates a novel use of the U-Net architecture in the field of semantic segmentation to detect landforms using preprocessed satellite imagery. The study applies the U-Net model for effective feature extraction by using Convolutional Neural Network (CNN) segmentation techniques. Dropout is strategically used for regularization to improve the model's perseverance, and the Adam optimizer is used for effective training. The study thoroughly assesses the performance of the U-Net architecture utilizing a large sample of preprocessed satellite topographical images. The model excels in semantic segmentation tasks, displaying high-resolution outputs, quick feature extraction, and flexibility to a wide range of applications. The findings highlight the U-Net architecture's substantial contribution to the advancement of machine learning and image processing technologies. The U-Net approach, which emphasizes pixel-wise categorization and comprehensive segmentation map production, is helpful in practical applications such as autonomous driving, disaster management, and land use planning. This study not only investigates the complexities of U-Net architecture for semantic segmentation, but also highlights its real-world applications in image classification, analysis, and landform identification. The study demonstrates the U-Net model's key significance in influencing the environment of modern technology.
Open AccessConvolutional Neural Network Segmentation for Satellite Imagery Data to Identify Landforms Using U-Net Architecture
This study demonstrates a novel use of the U-Net architecture in the field of semantic segmentation to detect landforms using preprocessed satellite imagery. The study applies the U-Net model for effective feature extraction by using Convolutional Neural Network (CNN) segmentation techniques. Dropout is strategically used for regularization to improve the model's perseverance, and the Adam optimizer is used for effective training. The study thoroughly assesses the performance of the U-Net architecture utilizing a large sample of preprocessed satellite topographical images. The model excels in semantic segmentation tasks, displaying high-resolution outputs, quick feature extraction, and flexibility to a wide range of applications. The findings highlight the U-Net architecture's substantial contribution to the advancement of machine learning and image processing technologies. The U-Net approach, which emphasizes pixel-wise categorization and comprehensive segmentation map production, is helpful in practical applications such as autonomous driving, disaster management, and land use planning. This study not only investigates the complexities of U-Net architecture for semantic segmentation, but also highlights its real-world applications in image classification, analysis, and landform identification. The study demonstrates the U-Net model's key significance in influencing the environment of modern technology.
- Open Access
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 703-710
Numin: Weighted-Majority Ensembles for Intraday Trading
We consider the application of machine learning models for short-term intra-day trading in equities. We envisage a scenario wherein machine learning models are submitted by independent data scientists to predict discretised ten-candle returns every five minutes, in response to five-minute candlestick data provided to them in near real-time. An ensemble model combines these multiple models via a weighted-majority algorithm. The weights of each model are dynamically updated based on the performance of each model, and can also be used to reward model owners. Each model’s performance is evaluated according to two different metrics over a recent time window: In addition to accuracy, we also consider a ‘utility’ metric that is a proxy for a model’s potential profitability under a particular trading strategy. We present experimental results on real intra-day data that show that our weighted-majority ensemble techniques show improved accuracy as well as utility over any of the individual models, especially using the utility metric to dynamically re-weight models over shorter time-windows.
- 14 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 703-710
Open AccessNumin: Weighted-Majority Ensembles for Intraday Trading
We consider the application of machine learning models for short-term intra-day trading in equities. We envisage a scenario wherein machine learning models are submitted by independent data scientists to predict discretised ten-candle returns every five minutes, in response to five-minute candlestick data provided to them in near real-time. An ensemble model combines these multiple models via a weighted-majority algorithm. The weights of each model are dynamically updated based on the performance of each model, and can also be used to reward model owners. Each model’s performance is evaluated according to two different metrics over a recent time window: In addition to accuracy, we also consider a ‘utility’ metric that is a proxy for a model’s potential profitability under a particular trading strategy. We present experimental results on real intra-day data that show that our weighted-majority ensemble techniques show improved accuracy as well as utility over any of the individual models, especially using the utility metric to dynamically re-weight models over shorter time-windows.
- 7 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 5618-5627
QuARCS: Quantum Anomaly Recognition and Caption Scoring Framework for Surveillance Videos
Traditional surveillance video stream monitoring demands manual analysis, often leading to inaccuracies. While recent advancements have enabled automated analysis in surveillance video stream monitoring, challenges persist in achieving high accuracy and efficiency. Thus, an automated system is needed to monitor and report on video streams in real-time or retrospectively within surveillance networks, alleviating human error and inefficiency. Our paper, presents a comprehensive framework that integrates a hybrid quantum-classical anomaly detection system, a caption-generating model, and a novel Text-Driven Urgency Rating Model (T-DURM) trained using a newly created labelled dataset called UCFC-CUR which prioritises crimes based on their urgency. The hybrid classifier outperforms its direct classical counterpart by 7.7%. The aforementioned pipeline possesses the capability to identify anomalous occurrences from surveillance videos, generate a textual representation of the event, and assign a numerical value indicating the level of urgency associated with the specific anomaly. The hybrid anomaly detection model achieved an AUC of 82.80 surpassing the classical model’s AUC of 75.14. While the newly proposed T-DRUM achieves a R2 score of 0.982.
- 7 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Consumer Electronics
- Vol. 70 (3) , 5618-5627
QuARCS: Quantum Anomaly Recognition and Caption Scoring Framework for Surveillance Videos
Traditional surveillance video stream monitoring demands manual analysis, often leading to inaccuracies. While recent advancements have enabled automated analysis in surveillance video stream monitoring, challenges persist in achieving high accuracy and efficiency. Thus, an automated system is needed to monitor and report on video streams in real-time or retrospectively within surveillance networks, alleviating human error and inefficiency. Our paper, presents a comprehensive framework that integrates a hybrid quantum-classical anomaly detection system, a caption-generating model, and a novel Text-Driven Urgency Rating Model (T-DURM) trained using a newly created labelled dataset called UCFC-CUR which prioritises crimes based on their urgency. The hybrid classifier outperforms its direct classical counterpart by 7.7%. The aforementioned pipeline possesses the capability to identify anomalous occurrences from surveillance videos, generate a textual representation of the event, and assign a numerical value indicating the level of urgency associated with the specific anomaly. The hybrid anomaly detection model achieved an AUC of 82.80 surpassing the classical model’s AUC of 75.14. While the newly proposed T-DRUM achieves a R2 score of 0.982.
- 13 June 2024
- Published by Springer Nature in Cognitive Computation
- Vol. 16 (5) , 2131-2153
Advancing Medical Imaging Through Generative Adversarial Networks: A Comprehensive Review and Future Prospects
- 13 June 2024
- Published by Springer Nature in Cognitive Computation
- Vol. 16 (5) , 2131-2153
Advancing Medical Imaging Through Generative Adversarial Networks: A Comprehensive Review and Future Prospects