Deep learning provides new data-driven tools to relate neural activity to perception and cognition, aiding scientists in developing theories of neural computation that increasingly resemble biological systems both at the level of behavior and of neural activity. But what in a deep neural network should correspond to what in a biological system? This question is addressed implicitly in the use of comparison measures that relate specific neural or behavioral dimensions via a particular functional form. However, distinct comparison methodologies can give conflicting results in recovering even a known ground-truth model in an idealized setting, leaving open the question of what to conclude from the outcome of a systems comparison using any given methodology. Here, we develop a framework to make explicit and quantitative the effect of both hypothesis-driven aspects—such as details of the architecture of a deep neural network—as well as methodological choices in a systems comparison setting. We demonstrate via the learning dynamics of deep neural networks that, while the role of the comparison methodology is often de-emphasized relative to hypothesis-driven aspects, this choice can impact and even invert the conclusions to be drawn from a comparison between neural systems. We provide evidence that the right way to adjudicate a comparison depends on the use case—the scientific hypothesis under investigation—which could range from identifying single-neuron or circuit-level correspondences to capturing generalizability to new stimulus properties

Understanding Human ability to learn novel concepts from just a few sensory experiences is a fundamental problem in cognitive neuroscience. I will describe a recent work with Ben Sorcher and Surya Ganguli (PNAS, October 2022) in which we propose a simple, biologically plausible, and mathematically tractable neural mechanism for few-shot learning of naturalistic concepts. We posit that the concepts that can be learned from few examples are defined by tightly circumscribed manifolds in the neural firing-rate space of higher-order sensory areas. Discrimination between novel concepts is performed by downstream neurons implementing ‘prototype’ decision rule, in which a test example is classified according to the nearest prototype constructed from the few training examples. We show that prototype few-shot learning achieves high few-shot learning accuracy on natural visual concepts using both macaque inferotemporal cortex representations and deep neural network (DNN) models of these representations. We develop a mathematical theory that links few-shot learning to the geometric properties of the neural concept manifolds and demonstrate its agreement with our numerical simulations across different DNNs as well as different layers. Intriguingly, we observe striking mismatches between the geometry of manifolds in intermediate stages of the primate visual pathway and in trained DNNs. Finally, we show that linguistic descriptors of visual concepts can be used to discriminate images belonging to novel concepts, without any prior visual experience of these concepts (a task known as ‘zero-shot’ learning), indicated a remarkable alignment of manifold representations of concepts in visual and language modalities. I will discuss ongoing effort to extend this work to other high level cognitive tasks.

The brain represents the external world through the bottleneck of sensory organs. The network of hierarchically organized neurons is thought to recover the causes of sensory inputs to reconstruct the reality in the brain in idiosyncratic ways depending on individuals and their internal states. How can we understand the world model represented in an individual’s brain, or the neuroverse? My lab has been working on brain decoding of visual perception and subjective experiences such as imagery and dreaming using machine learning and deep neural network representations. In this talk, I will outline the progress of brain decoding methods and present how subjective experiences are externalized as images and how they could be shared across individuals via neural code conversion. The prospects of these approaches in basic science and neurotechnology will be discussed.

Modeling neural responses to naturalistic stimuli has been instrumental in advancing our understanding of the visual system. Dominant computational modeling efforts in this direction have been deeply rooted in preconceived hypotheses. In contrast, hypothesis-neutral computational methodologies with minimal apriorism which bring neuroscience data directly to bear on the model development process are likely to be much more flexible and effective in modeling and understanding tuning properties throughout the visual system. In this study, we develop a hypothesis-neutral approach and characterize response selectivity in the human visual cortex exhaustively and systematically via response-optimized deep neural network models. First, we leverage the unprecedented scale and quality of the recently released Natural Scenes Dataset to constrain parametrized neural models of higher-order visual systems and achieve novel predictive precision, in some cases, significantly outperforming the predictive success of state-of-the-art task-optimized models. Next, we ask what kinds of functional properties emerge spontaneously in these response-optimized models? We examine trained networks through structural ( feature visualizations) as well as functional analysis (feature verbalizations) by running `virtual' fMRI experiments on large-scale probe datasets. Strikingly, despite no category-level supervision, since the models are solely optimized for brain response prediction from scratch, the units in the networks after optimization act as detectors for semantic concepts like `faces' or `words', thereby providing one of the strongest evidences for categorical selectivity in these visual areas. The observed selectivity in model neurons raises another question: are the category-selective units simply functioning as detectors for their preferred category or are they a by-product of a non-category-specific visual processing mechanism? To investigate this, we create selective deprivations in the visual diet of these response-optimized networks and study semantic selectivity in the resulting `deprived' networks, thereby also shedding light on the role of specific visual experiences in shaping neuronal tuning. Together with this new class of data-driven models and novel model interpretability techniques, our study illustrates that DNN models of visual cortex need not be conceived as obscure models with limited explanatory power, rather as powerful, unifying tools for probing the nature of representations and computations in the brain.

Our visual experience of living in a three-dimensional world is created from the information contained in the two-dimensional images projected into our eyes. The overlapping visual fields of the two eyes mean that their images are highly correlated, and that the small differences that are present represent an important cue to depth. Binocular neurons encode this information in a way that both maximises efficiency and optimises disparity tuning for the depth structures that are found in our natural environment. Neural network models provide a clear account of how these binocular neurons encode the local binocular disparity in images. These models can be expanded to multi-layer models that are sensitive to salient features of scenes, such as the orientations and discontinuities between surfaces. These deep neural network models have also shown the importance of binocular disparity for the segmentation of images into separate objects, in addition to the estimation of distance. These results demonstrate the usefulness of machine learning approaches as a tool for understanding biological vision.

Materials with complex appearances, like textiles and foodstuffs, pose challenges for conventional theories of vision. How does the brain learn to see properties of the world—like the glossiness of a surface—that cannot be measured by any other senses? Recent advances in unsupervised deep learning may help shed light on material perception. I will show how an unsupervised deep neural network trained on an artificial environment of surfaces that have different shapes, materials and lighting, spontaneously comes to encode those factors in its internal representations. Most strikingly, the model makes patterns of errors in its perception of material that follow, on an image-by-image basis, the patterns of errors made by human observers. Unsupervised deep learning may provide a coherent framework for how many perceptual dimensions form, in material perception and beyond.

The success of deep learning sparked interest in whether the brain learns by using similar techniques for assigning credit to each synaptic weight for its contribution to the network output. However, the majority of current attempts at biologically-plausible learning methods are either non-local in time, require highly specific connectivity motives, or have no clear link to any known mathematical optimization method. Here, we introduce Deep Feedback Control (DFC), a new learning method that uses a feedback controller to drive a deep neural network to match a desired output target and whose control signal can be used for credit assignment. The resulting learning rule is fully local in space and time and approximates Gauss-Newton optimization for a wide range of feedback connectivity patterns. To further underline its biological plausibility, we relate DFC to a multi-compartment model of cortical pyramidal neurons with a local voltage-dependent synaptic plasticity rule, consistent with recent theories of dendritic processing. By combining dynamical system theory with mathematical optimization theory, we provide a strong theoretical foundation for DFC that we corroborate with detailed results on toy experiments and standard computer-vision benchmarks.

The possibilities of machine learning and neural networks in particular are ever expanding. With increased opportunities to do good, however there are just as many opportunities to do harm and even in the case that good intentions are at the helm, evidence suggests that opportunities for good may eventually prove to be the opposite. The greatest threat to what machine learning is able to achieve and to us as humans, is machine learning that does not reflect the diversity of the users it is meant to serve. It is important that we are not so pre-occupied with advancing technology into the future that we have not taken the time to invest the energy into engineering the security measures this future requires. It is important to investigate now, as thoroughly as we investigate differing deep neural network architectures, the complex questions regarding the fact that humans and the society in which they operate is inherently biased and loaded with prejudice and that these traits find themselves in the machines we create (and increasingly allow to run our lives).