Ajay Subramanian

I use psychophysical methods to probe the differences between human and machine vision. I am currently studying the computations that make human object recognition more robust than neural network recognition, towards building more robust deep learning systems. I am a PhD student in Cognition & Perception at New York University, advised by Denis Pelli. Previously, I completed my undergraduate degree in Electronics and Communication Engineering at BITS Pilani, India. My broad interests are in understanding and developing deep learning systems using ideas from human psychology and neuroscience.

• Subramanian, A., Sizikova, E., Majaj, N. J., Pelli, D. G. (2023). Spatial-frequency channels, shape bias, and adversarial robustness. To appear in Advances in neural information processing systems (NeurIPS), 36
• Subramanian, A., Chitlangia, S., Baths, V. (2022). Reinforcement learning and its connections with neuroscience and psychology. Neural Networks, 145, 271-287.
• Turner, J. P., Knight, J. C., Subramanian, A., Nowotny, T. (2022). mlGeNN: accelerating SNN inference using GPU-enabled neural networks. Neuromorphic Computing and Engineering, 2(2), 024002.

• Zhou, J. Y., Chun, C., Subramanian, A., Simoncelli, E. P. (2023). Comparing models of neural representation based on their metric tensors. In preparation.
• Tsividis, P., Loula, J., Burga, J., Rodriguez, J. P., Arnaud, S., Foss, N., Campero, A., Subramanian, A., Pouncy, T., Gershman, S., Tenenbaum, J. B. (2023). Human Learning of Complex Novel Tasks as Theory-Based Modeling, Exploration, and Planning. Under review in PNAS.
• Subramanian, A., Price, S., Sizikova, E., Kumbhar, O., Majaj, N. J., Pelli, D. G. (arXiv, 2022). SATBench: Benchmarking the speed-accuracy tradeoff in object recognition by humans and dynamic neural networks. arXiv.

• Subramnian, A., Patil, R., Baths, V. (2020). Word2Brain2Image: A data-driven approach towards understanding representations in the brain. Round table track: Data issues in Cognitive Neuroscience, International CCCP Symposium. Virtual.

• Subramanian, A., Sizikova, E., Majaj, N. J., Pelli, D. G. (2023). Spatial-frequency channels for object recognition by neural networks are twice as wide as those of humans. An explanation for shape bias? ECVP, Paphos, Cyprus.
• Subramanian, A., Sizikova, E., Majaj, N. J., Pelli, D. G. (2023). Spatial-frequency channels for object recognition by neural networks are twice as wide as those of humans. VSS Meeting, St. Pete Beach, USA.
• Zhou, J. Y., Chun, C., Subramanian, A., Simoncelli, E., P. (2023). Computing and comparing metric tensors in neural response models. VSS Meeting, St. Pete Beach, USA.
• Subramanian, A., Sizikova, E., Majaj, N. J., Pelli, D. G. (2023). Spatial-frequency channels for object recognition by neural networks are twice as wide as those of humans. COSYNE, Montreal, Canada.
• Subramanian, A., Price, S., Sizikova, E., Kumbhar, O., Majaj, N., Pelli, D. G. (2022). Benchmarking dynamic neural-network models of the human speed-accuracy tradeoff. VSS Meeting, St. Pete Beach, USA.
• Subramanian, A., Patil, R., Baths, V. (2022). Word2Brain2Image: Visual Reconstruction from Spoken Word Representations. ACCS, Goa, India.