Neehar Kondapaneni - Academia.edu (original) (raw)

Uploads

Papers by Neehar Kondapaneni

arXiv (Cornell University), Sep 28, 2023

arXiv (Cornell University), Dec 7, 2020

The ability to understand and manipulate numbers and quantities emerges during childhood, but the... more The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which humans acquire and develop this ability is still poorly understood. We explore this question through a model, assuming that the learner is able to pick up and place small objects from, and to, locations of its choosing, and will spontaneously engage in such undirected manipulation. We further assume that the learner's visual system will monitor the changing arrangements of objects in the scene and will learn to predict the effects of each action by comparing perception with a supervisory signal from the motor system. We model perception using standard deep networks for feature extraction and classification, and gradient descent learning. Our main finding is that, from learning the task of action prediction, an unexpected image representation emerges exhibiting regularities that foreshadow the perception and representation of numbers and quantity. These include distinct categories for zero and the first few natural numbers, a strict ordering of the numbers, and a one-dimensional signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate numerosity, i.e. the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. Remarkably, subitization and numerosity estimation extrapolate to scenes containing many objects, far beyond the three objects used during training. We conclude that important aspects of a facility with numbers and quantities may be learned with supervision from a simple pre-training task. Our observations suggest that cross-modal learning is a powerful learning mechanism that may be harnessed in artificial intelligence.

arXiv (Cornell University), Dec 7, 2020

The ability to understand and manipulate numbers and quantities emerges during childhood, but the... more The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which this ability is developed is still poorly understood. In particular, it is not known whether acquiring such a number sense is possible without supervision from a teacher. To explore this question, we propose a model in which spontaneous and undirected manipulation of small objects trains perception to predict the resulting scene changes. We find that, from this task, an image representation emerges that exhibits regularities that foreshadow numbers and quantity. These include distinct categories for zero and the first few natural numbers, a notion of order, and a signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. We conclude that important aspects of a facility with numbers and quantities may be learned without explicit teacher supervision.

arXiv (Cornell University), Jul 20, 2022

Each year, thousands of people learn new visual categorization tasks-radiologists learn to recogn... more Each year, thousands of people learn new visual categorization tasks-radiologists learn to recognize tumors, birdwatchers learn to distinguish similar species, and crowd workers learn how to annotate valuable data for applications like autonomous driving. As humans learn, their brain updates the visual features it extracts and attend to, which ultimately informs their final classification decisions. In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks. We propose models that jointly extract the visual features used by learners as well as predicting the classification functions they utilize. We collect three challenging new datasets from real human learners in order to evaluate the performance of different visual knowledge tracing methods. Our results show that our recurrent models are able to predict the classification behavior of human learners on three challenging medical image and species identification tasks.

Neuron, Jan 17, 2017

Learning involves a transformation of brain-wide operation dynamics. However, our understanding o... more Learning involves a transformation of brain-wide operation dynamics. However, our understanding of learning-related changes in macroscopic dynamics is limited. Here, we monitored cortex-wide activity of the mouse brain using wide-field calcium imaging while the mouse learned a motor task over weeks. Over learning, the sequential activity across cortical modules became temporally more compressed, and its trial-by-trial variability decreased. Moreover, a new flow of activity emerged during learning, originating from premotor cortex (M2), and M2 became predictive of the activity of many other modules. Inactivation experiments showed that M2 is critical for the post-learning dynamics in the cortex-wide activity. Furthermore, two-photon calcium imaging revealed that M2 ensemble activity also showed earlier activity onset and reduced variability with learning, which was accompanied by changes in the activity-movement relationship. These results reveal newly emergent properties of macrosco...

arXiv (Cornell University), May 24, 2024

arXiv (Cornell University), Sep 28, 2023

arXiv (Cornell University), Dec 7, 2020

The ability to understand and manipulate numbers and quantities emerges during childhood, but the... more The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which humans acquire and develop this ability is still poorly understood. We explore this question through a model, assuming that the learner is able to pick up and place small objects from, and to, locations of its choosing, and will spontaneously engage in such undirected manipulation. We further assume that the learner's visual system will monitor the changing arrangements of objects in the scene and will learn to predict the effects of each action by comparing perception with a supervisory signal from the motor system. We model perception using standard deep networks for feature extraction and classification, and gradient descent learning. Our main finding is that, from learning the task of action prediction, an unexpected image representation emerges exhibiting regularities that foreshadow the perception and representation of numbers and quantity. These include distinct categories for zero and the first few natural numbers, a strict ordering of the numbers, and a one-dimensional signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate numerosity, i.e. the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. Remarkably, subitization and numerosity estimation extrapolate to scenes containing many objects, far beyond the three objects used during training. We conclude that important aspects of a facility with numbers and quantities may be learned with supervision from a simple pre-training task. Our observations suggest that cross-modal learning is a powerful learning mechanism that may be harnessed in artificial intelligence.

arXiv (Cornell University), Dec 7, 2020

The ability to understand and manipulate numbers and quantities emerges during childhood, but the... more The ability to understand and manipulate numbers and quantities emerges during childhood, but the mechanism through which this ability is developed is still poorly understood. In particular, it is not known whether acquiring such a number sense is possible without supervision from a teacher. To explore this question, we propose a model in which spontaneous and undirected manipulation of small objects trains perception to predict the resulting scene changes. We find that, from this task, an image representation emerges that exhibits regularities that foreshadow numbers and quantity. These include distinct categories for zero and the first few natural numbers, a notion of order, and a signal that correlates with numerical quantity. As a result, our model acquires the ability to estimate the number of objects in the scene, as well as subitization, i.e. the ability to recognize at a glance the exact number of objects in small scenes. We conclude that important aspects of a facility with numbers and quantities may be learned without explicit teacher supervision.

arXiv (Cornell University), Jul 20, 2022

Each year, thousands of people learn new visual categorization tasks-radiologists learn to recogn... more Each year, thousands of people learn new visual categorization tasks-radiologists learn to recognize tumors, birdwatchers learn to distinguish similar species, and crowd workers learn how to annotate valuable data for applications like autonomous driving. As humans learn, their brain updates the visual features it extracts and attend to, which ultimately informs their final classification decisions. In this work, we propose a novel task of tracing the evolving classification behavior of human learners as they engage in challenging visual classification tasks. We propose models that jointly extract the visual features used by learners as well as predicting the classification functions they utilize. We collect three challenging new datasets from real human learners in order to evaluate the performance of different visual knowledge tracing methods. Our results show that our recurrent models are able to predict the classification behavior of human learners on three challenging medical image and species identification tasks.

Neuron, Jan 17, 2017

Learning involves a transformation of brain-wide operation dynamics. However, our understanding o... more Learning involves a transformation of brain-wide operation dynamics. However, our understanding of learning-related changes in macroscopic dynamics is limited. Here, we monitored cortex-wide activity of the mouse brain using wide-field calcium imaging while the mouse learned a motor task over weeks. Over learning, the sequential activity across cortical modules became temporally more compressed, and its trial-by-trial variability decreased. Moreover, a new flow of activity emerged during learning, originating from premotor cortex (M2), and M2 became predictive of the activity of many other modules. Inactivation experiments showed that M2 is critical for the post-learning dynamics in the cortex-wide activity. Furthermore, two-photon calcium imaging revealed that M2 ensemble activity also showed earlier activity onset and reduced variability with learning, which was accompanied by changes in the activity-movement relationship. These results reveal newly emergent properties of macrosco...

arXiv (Cornell University), May 24, 2024