United States

Mail privacy protection aims to prevent unauthorized access to hidden content within an envelope since normal paper envelopes are not as safe as we think. In this paper, for the first time, we show that with a well designed deep learning model, the hidden content may be largely recovered without opening the envelope. We start by modeling deep learning-based privacy attacks on physical mail content as learning the mapping from the camera-captured envelope front face image to the hidden content, then we explicitly model the mapping as a combination of perspective transformation, image dehazing and denoising using a deep convolutional neural network, named Neural-STE (See-Through-Envelope). We show experimentally that hidden content details, such as texture and image structure, can be clearly recovered. Finally, our formulation and model allow us to design envelopes that can counter deep learning-based privacy attacks on physical mail.

AAAI 2021

Modeling Deep Learning Based Privacy Attacks on Physical Mail

Colleagues and Friends:

I am very happy to welcome you to the 14th annual Canadian Neuroscience Meeting, and to the first virtual edition of our meeting. I want to highlight the important work the CAN meeting chair, **Roger Thompson** and co-chair, **Alyson Fournier**, did to put together the great program we are offering this year. Moving to a virtual format required a complete re-design of the program, and both Roger and Alyson did a splendid job in providing us with an appealing and well adapted program for our first virtual event. I wish to thank them for this very important effort.

Highlights of this year’s scientific meeting include invited speakers **Michael Hausser, Franck Polleux, Gwyneth Card, Magdalena Götz**and Brain Prize winner **Huda Zoghbi**. Plenary and parallel symposia, proposed by our members complete our diverse [scientific program.](https://can-acn.org/meeting-2021/program-2021/)

The 2021 Advocacy session, chaired and organized by CAN advocacy committee chair **Karun Singh**, will feature a special lecture and question period with Member of Parliament and past Science Minister **Kirsty Duncan**. This will be followed by a short overview of CAN’s advocacy activities over the last year. We invite you to participate in this session for insight from Dr. Duncan on the workings of Parliament Hill, and to learn more about what CAN has been doing to promote neuroscience research in Canada.

We are also excited to host **Lisa Willis** in the Equity Diversity and Inclusion session, organized by EDI committee chair **Jibran Khokhar**.

A special highlight of our meeting will be the lectures by award-winning young neuroscientists. We are please to host the CAN 2020 Young Investigator Award winner **Mihaela Iordanova**, and CAN 2021 Young Investigator Award winners **Aaron Phillips** and **Tabrez Siddiqui**. Highlights will also include presentation by the top three winners of the CAN-CIHR-INMHA Brain Star Award winners, **Claire Gizowski, Nuria Daviu Abant** and **Lukas Tamayo-Orrego**.

Independently organized satellite symposia complement and complete this exciting program, check them out here: https://can-acn.org/meeting-2021/2021-satellite-symposia/

Some of the most engaging sessions are always the poster sessions featuring the work of our trainees, so make sure to log in to Gather Town during the poster sessions to chat with the presenters.
We hope you enjoy this program, and look forward to welcoming you, virtually.

Shernaz Bamji

President of the Canadian Association for Neuroscience

![](https://assets.underline.io/uploads/markdown_image/1/image/b9aea25343a87d5aac3b9367dc780974.jpg)



Please head to https://can-acn.org/meeting-2021/registration-2021/ to register. 

CAN-ACN 2021

14th Canadian Neuroscience Meeting from August 23rd-25th

technical paper

The purpose of the AAAI conference is to promote research in artificial intelligence (AI) and scientific exchange among AI researchers, practitioners, scientists, and engineers in affiliated disciplines. 

Bayesian neural networks (BNN) can estimate the uncertainty in predictions, as opposed to non-Bayesian neural networks (NNs). However, BNNs have been far less widely used than non-Bayesian NNs in practice since they need iterative NN executions to predict a result for one data, and it gives rise to prohibitive computational cost. This computational burden is a critical problem when processing data streams with low-latency. To address this problem, we propose a novel model VQ-BNN, which approximates BNN inference for data streams. In order to reduce the computational burden, VQ-BNN inference predicts NN only once and compensates the result with previously memorized predictions. To be specific, VQ-BNN inference for data streams is given by temporal exponential smoothing of recent predictions. The computational cost of this model is almost the same as that of non-Bayesian NNs. Experiments including semantic segmentation on real-world data show that this model performs significantly faster than BNNs while estimating predictive results comparable to or superior to the results of BNNs.

Vector Quantized Bayesian Neural Network Inference for Data Streams

This paper explores the behavior of present-biased agents, that is, agents who erroneously anticipate the costs of future actions compared to their real costs. Specifically, the paper extends the origi- nal framework proposed by Akerlof (1991) for studying various aspects of human behavior related to time-inconsistent planning, including pro- crastination, and abandonment, as well as the elegant graph-theoretic model encapsulating this framework recently proposed by Kleinberg and Oren (2014). The benefit of this extension is twofold. First, it enables to perform fine grained analysis of the behavior of present-biased agents depending on the optimisation task they have to perform. In particular, we study covering tasks vs. hitting tasks, and show that the ratio be- tween the cost of the solutions computed by present-biased agents and the cost of the optimal solutions may differ significantly depending on the problem constraints. Second, our extension enables to study not only un- derestimation of future costs, coupled with minimization problems, but also all combinations of minimization/maximization, and underestima- tion/overestimation. We study the four scenarios, and we establish upper bounds on the cost ratio for three of them (the cost ratio for the origi- nal scenario was known to be unbounded), providing a complete global picture of the behavior of present-biased agents, as far as optimisation tasks are concerned.

Present-Biased Optimization

Feature selection reduces the dimensionality of data by identifying a subset of the most informative features. In this paper, we propose an innovative framework for unsupervised feature selection, called fractal autoencoders (FAE). It trains a neural network to pinpoint informative features for global exploring of representability and for local excavating of diversity. Architecturally, FAE extends autoencoders by adding a one-to-one scoring layer and a small sub-neural network for feature selection in an unsupervised fashion. With such a concise architecture, FAE achieves state-of-the-art performances; extensive experimental results on fourteen datasets, including very high-dimensional data, have demonstrated the superiority of FAE over existing contemporary methods for unsupervised feature selection. In particular, FAE exhibits substantial advantages on gene expression data exploration, reducing measurement cost by about 15% over the widely used L1000 landmark genes. Further, we show that the FAE framework is easily extensible with an application.

Fractal Autoencoders for Feature Selection

Learned image compression has recently shown the potential to outperform the standard codecs. State-of-the-art rate-distortion (R-D) performance has been achieved by context-adaptive entropy coding approaches in which hyperprior and autoregressive models are jointly utilized to effectively capture the spatial dependencies in the latent representations. However, the latents are feature maps of the same spatial resolution in previous works, which contain some redundancies that affect the R-D performance. In this paper, we propose a learned bi-resolution image coding approach that is based on the recently developed octave convolutions to factorize the latents into high and low resolution components. Therefore, the spatial redundancy is reduced, which improves the R-D performance. Novel generalized octave convolution and octave transposed-convolution architectures with internal activation layers are also proposed to preserve more spatial structure of the information. Experimental results show that the proposed scheme outperforms all existing learned methods as well as standard codecs such as the next-generation video coding standard VVC (4:2:0) in both PSNR and MS-SSIM. We also show that the proposed generalized octave convolution can improve the performance of other auto-encoder-based schemes such as semantic segmentation and image denoising.

Learned Bi-Resolution Image Coding Using Generalized Octave Convolutions

Sequential sensor data is generated in a wide variety of real-world applications. A fundamental machine learning challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent years within domains such as speech, this has relied on the availability of large datasets of sequences with high-quality labels. In many applications, however, the associated class labels are often extremely limited, with precise labelling/segmentation being too expensive to perform in a high volume. However, large amounts of unlabelled data may still be available.  In this paper we propose a novel framework for semi-supervised learning in such contexts. In an unsupervised manner, change-point detection methods can be used to identify instances where classes change within in a sequence.  We show that change points provide examples of similar/dissimilar pairs of sequences which, when coupled with class labels, can be used in a semi-supervised classification setting. Pairs from labels and change points are used by a neural network to learn improved representations for classification. We provide extensive synthetic simulations and show that the learned representations are better than those learned through an autoencoder and obtain improved results on simulations and human activity recognition datasets.

Semi-Supervised Sequence Classification through Change Point Detection

We explore the potential of continuous local search (CLS) in SAT solving by proposing a novel approach for finding a solution of a hybrid system of Boolean constraints. The algorithm is based on CLS combined with belief propagation on binary decision diagrams (BDDs). Our framework accepts all Boolean constraints that admit compact BDDs, including symmetric Boolean constraints and small-coefficient pseudo-Boolean constraints as interesting families. We propose a novel algorithm for efficiently computing the gradient needed by CLS. We study the capabilities and limitations of our versatile CLS solver, GradSAT, by applying it on many benchmark instances.  The experimental results indicate that GradSAT can be a useful addition to the portfolio of existing SAT and MaxSAT solvers for solving Boolean satisfiability and optimization problems.

On Continuous Local BDD-Based Search for Hybrid SAT Solving

Most widely-used convolutional neural networks (CNNs) end up with a global average pooling layer and a fully-connected layer. In this pipeline, a certain class is represented by one template vector preserved in the feature banks of fully-connected layer. Yet, a class may have multiple properties useful for recognition while the above formulation only captures one of them. Therefore, it is desired to represent a class by multiple proxies. However, directly adding multiple linear layers turns out to be a trivial solution as no improvement can be observed. To tackle this problem, we adopt optimal transport theory to calculate a non-uniform matching flow between the elements in the feature map of a sample and the proxies of a class in a closed way. By doing so, the models are enabled to achieve partial matching as both the feature maps and the proxy set can now focus on a subset of elements from the counterpart. Such formulation also enables us to embed the samples into the Wasserstein metric space, which has many advantages over the original Euclidean space. This formulation can be achieved by a lightweight iterative algorithm, which can be easily embedded into the automatic differentiation framework. Empirical studies are performed on two widely-used classification datasets, CIFAR, and ILSVRC2012, and the substantial improvements on these two benchmarks demonstrate the effectiveness of our method.

Multi-Proxy Wasserstein Classifier for Image Classification

We consider the problem of knowledge transfer when an agent is facing a series of Reinforcement Learning (RL) tasks. We introduce a novel metric between Markov Decision Processes and establish that close MDPs have close optimal value functions. Formally, the optimal value functions are Lipschitz continuous with respect to the tasks space. These theoretical results lead us to a value-transfer method for Lifelong RL, which we use to build a PAC-MDP algorithm with improved convergence rate. Further, we show the method to experience no negative transfer with high probability. We illustrate the benefits of the method in Lifelong RL experiments.

Lipschitz Lifelong Reinforcement Learning

We study decentralized stochastic linear bandits, where a network of N agents acts cooperatively to efficiently solve a linear bandit-optimization problem over a d-dimensional space.  For this problem, we propose DLUCB: a fully decentralized algorithm that minimizes the cumulative regret over the entire network. At each round of the algorithm each agent chooses its actions following an upper confidence bound (UCB) strategy and agents share information with their immediate neighbors through a carefully designed consensus procedure that repeats over cycles. Our analysis adjusts the duration of these communication cycles ensuring near-optimal regret performance O(d \log{NT}\sqrt{NT}) at a communication rate of O(dN^2) per round. The structure of the network affects the regret performance via a small additive term â€“ coined the regret of delay â€“ that depends on the spectral gap of the underlying graph. Notably, our results apply to arbitrary network topologies without a requirement for a dedicated agent acting as a server. In consideration of situations with high communication cost, we propose RC-DLUCB: a modification of DLUCB with rare communication among agents. The new algorithm trades off regret performance for a significantly reduced total communication cost of O(d^3N^5/2) over all T rounds. Finally, we show that our ideas extend naturally to the emerging, albeit more challenging, setting of safe bandits. For the recently studied problem of linear bandits with unknown linear safety constraints, we propose the first safe decentralized algorithm. Our study contributes towards applying bandit techniques in safety-critical distributed systems that repeatedly deal with unknown stochastic environments. We present numerical simulations for various network topologies that corroborate our theoretical findings.

Decentralized Multi-Agent Linear Bandits with Safety Constraints

We study MNL bandits, which is a variant of the traditional multi-armed bandit problem, under risk criteria. Unlike the ordinary expected revenue, risk criteria are more general goals widely used in industries and business. We design algorithms for a broad class of risk criteria, including but not limited to the well-known conditional value-at-risk, Sharpe ratio, and entropy risk, and prove that they suffer a near-optimal regret. As a complement, we also conduct experiments with both synthetic and real data to show the empirical performance of our proposed algorithms.

Downloads

Next from AAAI 2021

Vector Quantized Bayesian Neural Network Inference for Data Streams

Similar lecture

Second-order attribute of head motion is encoded at single-neuron level in the vestibular nuclei

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2021

Vector Quantized Bayesian Neural Network Inference for Data Streams

Similar lecture

Second-order attribute of head motion is encoded at single-neuron level in the vestibular nuclei

Downloads