This is an interesting paper on a mechanistic model of the ribbon synapse along with an ABC inference approach. Neither component is particularly novel, but the paper is thorough and compelling. The audience will likely be computationally-savvy experimental neuroscientists and those interested in applications of ABC; the former may be harder to find at NeurIPS, though they do exist. I encourage the authors to make the suggested revisions before the camera ready deadline.

The inherent noise of neural systems makes it difficult to construct models which accurately capture experimental measurements of their activity. While much research has been done on how to efficiently model neural activity with descriptive models such as linear-nonlinear-models (LN), Bayesian inference for mechanistic models has received considerably less attention. One reason for this is that these models typically lead to intractable likelihoods and thus make parameter inference difficult. Here, we develop an approximate Bayesian inference scheme for a fully stochastic, biophysically inspired model of glutamate release at the ribbon synapse, a highly specialized synapse found in different sensory systems. The model translates known structural features of the ribbon synapse into a set of stochastically coupled equations.

Mechanistic models of single-neuron dynamics have been extensively studied in computational neuroscience. However, identifying which models can quantitatively reproduce empirically measured data has been challenging. We propose to overcome this limitation by using likelihood-free inference approaches (also known as Approximate Bayesian Computation, ABC) to perform full Bayesian inference on single-neuron models. Our approach builds on recent advances in ABC by learning a neural network which maps features of the observed data to the posterior distribution over parameters. We learn a Bayesian mixture-density network approximating the posterior over multiple rounds of adaptively chosen simulations.

The authors present an Approximate Bayesian Computation approach to fitting dynamical systems models of single neuron dynamics. This is an interesting paper that aims to bring ABC to the neuroscience community. The authors introduce some tricks to handle the specifics of neuron models (handling bad simulations and bad features), and since fitting nonlinear single neuron models is typically quite painful, this could be a valuable tool. Overall, this paper is a real gem. My biggest issue is that, in its current form, many of the proposed improvements over [19] are a bit unclear in practice.

Partially observed stochastic reaction network (SRN) modeling the dynamics of a population of interacting species, such as chemical molecules participating in multiple reactions, is the fundamental building block of multi-scale bioprocess mechanistic model characterizing the causal interdependences from molecular-to macro-kinetics. It plays a critical role to: (1) facilitate digital twin development and support mechanism learning for biomanufacturing processes; (2) allow us to probe critical latent state based on partially observed information; and (3) serve as a fundamental model for a biofoundry platform [1] that can integrate heterogeneous online and offline measures collected from different manufacturing processes and speed up the bioprocess development with much less experiments. Model inference on the SRN mechanistic model based on heterogeneous data also helps to strengthen the theoretical foundations of federated learning on bioprocess mechanisms, through which we can train and advance knowledge. The SRN mechanistic model has three key features that make the model inference challenging. First, the continuoustime state transition model, representing the evolution of concentration or number of molecules, is highly nonlinear.

These devices serve as data collection powerhouses, continuously amassing vast repositories of personalized multi-modal data, which can include a wide array of input modalities such as text, images and videos. The potential locked within this trove of multi-modal data arriving continuously is immense, promising to unlock high-quality and tailored device-aware services for individual users. Despite promising, the personalized device service involves analyzing the dynamic nature of the multi-modal data that underscore users' intentions. The prevailing artificial intelligence (AI) systems, primarily trained and deployed in cloud-based environments, face a profound challenge in adapting to the dynamic device data when using a static cloud model for all individual users, mainly due to the distribution shift of the cloud and device data, as shown in Figure 1. In other words, high-quality personalized service requires AI systems to undergo continual refinement and adaptation to accommodate the evolving landscape of personalized multi-modal data. Intuitively, one of the straightforward adaptation strategies is to fine-tune the cloud model based on the device's multi-modal data, which can kindly alleviate the cloud-device data distribution shift to model users' intentions. Nevertheless, we contend that the fine-tuning-adaptation (FTA) paradigm may not satisfactorily resolve device model personalization, which can be summarized as two key aspects: (1) Undesirable Annotation.

Memristive devices have recently been proposed as efficient implementations of plastic synapses in neuromorphic systems. The plasticity in these memristive devices, i.e. their resistance change, is defined by the applied waveforms. This behavior resembles biological synapses, whose plasticity is also triggered by mechanisms that are determined by local waveforms. However, learning in memristive devices has so far been approached mostly on a pragmatic technological level. The focus seems to be on finding any waveform that achieves spike-timing-dependent plasticity (STDP), without regard to the biological veracity of said waveforms or to further important forms of plasticity.

Early stages of sensory systems face the challenge of compressing information from numerous receptors onto a much smaller number of projection neurons, a so called communication bottleneck. To make more efficient use of limited bandwidth, compression may be achieved using predictive coding, whereby predictable, or redundant, components of the stimulus are removed. In the case of the retina, Srinivasan et al. (1982) suggested that feedforward inhibitory connections subtracting a linear prediction generated from nearby receptors implement such compression, resulting in biphasic center-surround receptive fields. However, feedback inhibitory circuits are common in early sensory circuits and furthermore their dynamics may be nonlinear. Can such circuits implement predictive coding as well? Here, solving the transient dynamics of nonlinear reciprocal feedback circuits through analogy to a signal-processing algorithm called linearized Bregman iteration we show that nonlinear predictive coding can be implemented in an inhibitory feedback circuit.

Numerous mobile apps have leveraged deep learning capabilities. However, on-device models are vulnerable to attacks as they can be easily extracted from their corresponding mobile apps. Existing on-device attacking approaches only generate black-box attacks, which are far less effective and efficient than white-box strategies. This is because mobile deep learning frameworks like TFLite do not support gradient computing, which is necessary for white-box attacking algorithms. Thus, we argue that existing findings may underestimate the harmfulness of on-device attacks. To this end, we conduct a study to answer this research question: Can on-device models be directly attacked via white-box strategies? We first systematically analyze the difficulties of transforming the on-device model to its debuggable version, and propose a Reverse Engineering framework for On-device Models (REOM), which automatically reverses the compiled on-device TFLite model to the debuggable model. Specifically, REOM first transforms compiled on-device models into Open Neural Network Exchange format, then removes the non-debuggable parts, and converts them to the debuggable DL models format that allows attackers to exploit in a white-box setting. Our experimental results show that our approach is effective in achieving automated transformation among 244 TFLite models. Compared with previous attacks using surrogate models, REOM enables attackers to achieve higher attack success rates with a hundred times smaller attack perturbations. In addition, because the ONNX platform has plenty of tools for model format exchanging, the proposed method based on the ONNX platform can be adapted to other model formats. Our findings emphasize the need for developers to carefully consider their model deployment strategies, and use white-box methods to evaluate the vulnerability of on-device models.

Early stages of sensory systems face the challenge of compressing information from numerous receptors onto a much smaller number of projection neurons, a so called communication bottleneck. To make more efficient use of limited bandwidth, compression may be achieved using predictive coding, whereby predictable, or redundant, components of the stimulus are removed. In the case of the retina, Srinivasan et al. (1982) suggested that feedforward inhibitory connections subtracting a linear prediction generated from nearby receptors implement such compression, resulting in biphasic center-surround receptive fields. However, feedback inhibitory circuits are common in early sensory circuits and furthermore their dynamics may be nonlinear. Can such circuits implement predictive coding as well?