More Like this

1. Compressed Counting with Spiking Neurons (Extended Abstract)

   Hitron, Yael; Parter, Merav (January 2019, 7th Workshop on Biological Distributed Algorithms (BDA))

   We consider the task of measuring time with probabilistic threshold gates implemented by bio-inspired spiking neurons. In the model of spiking neural networks, network evolves in discrete rounds, where in each round, neurons fire in pulses in response to a sufficiently high membrane potential. This potential is induced by spikes from neighboring neurons that fired in the previous round, which can have either an excitatory or inhibitory effect. Discovering the underlying mechanisms by which the brain perceives the duration of time is one of the largest open enigma in computational neuroscience. To gain a better algorithmic understanding onto these processes, we introduce the neural timer problem. In this problem, one is given a time parameter t, an input neuron x, and an output neuron y. It is then required to design a minimum sized neural network (measured by the number of auxiliary neurons) in which every spike from x in a given round i, makes the output y fire for the subsequent t consecutive rounds.We first consider a deterministic implementation of a neural timer and show that Θ(logt)(deterministic) threshold gates are both sufficient and necessary. This raised the question of whether randomness can be leveraged to reduce the number of neurons. We answer this question in the affirmative by considering neural timers with spiking neurons where the neuron y is required to fire for t consecutive rounds with probability at least 1−δ, and should stop firing after at most 2 t rounds with probability 1−δ for some input parameter δ∈(0,1). Our key result is a construction of a neural timer with O(log log 1/δ) spiking neurons. Interestingly, this construction uses only one spiking neuron, while the remaining neurons can be deterministic threshold gates. We complement this construction with a matching lower bound of Ω(min{log log 1/δ,logt}) neurons. This provides the first separation between deterministic and randomized constructions in the setting of spiking neural networks.Finally, we demonstrate the usefulness of compressed counting networks for synchronizing neural networks. In the spirit of distributed synchronizers [Awerbuch-Peleg, FOCS’90], we provide a general transformation (or simulation) that can take any synchronized network solution and simulate it in an asynchronous setting (where edges have arbitrary response latencies) while incurring a small overhead w.r.t the number of neurons and computation time. 

   more » « less
2. Counting to Ten with Two Fingers: Compressed Counting with Spiking Neurons

   Hitron, Yael; Parter, Merav (September 2019, European Symposium on Algorithms (ESA))

   We consider the task of measuring time with probabilistic threshold gates implemented by bio-inspired spiking neurons. In the model of spiking neural networks, network evolves in discrete rounds, where in each round, neurons fire in pulses in response to a sufficiently high membrane potential. This potential is induced by spikes from neighboring neurons that fired in the previous round, which can have either an excitatory or inhibitory effect. We first consider a deterministic implementation of a neural timer and show that Θ(logt) (deterministic) threshold gates are both sufficient and necessary. This raised the question of whether randomness can be leveraged to reduce the number of neurons. We answer this question in the affirmative by considering neural timers with spiking neurons where the neuron y is required to fire for t consecutive rounds with probability at least 1−δ, and should stop firing after at most 2t rounds with probability 1−δ for some input parameter δ∈(0,1). Our key result is a construction of a neural timer with O(loglog1/δ) spiking neurons. Interestingly, this construction uses only one spiking neuron, while the remaining neurons can be deterministic threshold gates. We complement this construction with a matching lower bound of Ω(min{loglog1/δ,logt}) neurons. This provides the first separation between deterministic and randomized constructions in the setting of spiking neural networks. Finally, we demonstrate the usefulness of compressed counting networks for synchronizing neural networks. 

   more » « less
3. Variable Binding for Sparse Distributed Representations: Theory and Applications

   https://doi.org/10.1109/TNNLS.2021.3105949  

   Frady, Edward Paxon; Kleyko, Denis; Sommer, Friedrich T. (September 2021, IEEE Transactions on Neural Networks and Learning Systems)

   null (Ed.)

   Variable binding is a cornerstone of symbolic reasoning and cognition. But how binding can be implemented in connectionist models has puzzled neuroscientists, cognitive psychologists, and neural network researchers for many decades. One type of connectionist model that naturally includes a binding operation is vector symbolic architectures (VSAs). In contrast to other proposals for variable binding, the binding operation in VSAs is dimensionality-preserving, which enables representing complex hierarchical data structures, such as trees, while avoiding a combinatoric expansion of dimensionality. Classical VSAs encode symbols by dense randomized vectors, in which information is distributed throughout the entire neuron population. By contrast, in the brain, features are encoded more locally, by the activity of single neurons or small groups of neurons, often forming sparse vectors of neural activation. Following Laiho et al. (2015), we explore symbolic reasoning with a special case of sparse distributed representations. Using techniques from compressed sensing, we first show that variable binding in classical VSAs is mathematically equivalent to tensor product binding between sparse feature vectors, another well-known binding operation which increases dimensionality. This theoretical result motivates us to study two dimensionality-preserving binding methods that include a reduction of the tensor matrix into a single sparse vector. One binding method for general sparse vectors uses random projections, the other, block-local circular convolution, is defined for sparse vectors with block structure, sparse block-codes. Our experiments reveal that block-local circular convolution binding has ideal properties, whereas random projection based binding also works, but is lossy. We demonstrate in example applications that a VSA with block-local circular convolution and sparse block-codes reaches similar performance as classical VSAs. Finally, we discuss our results in the context of neuroscience and neural networks. 

   more » « less
4. TopoAct: Visually Exploring the Shape of Activations in Deep Learning

   https://doi.org/10.1111/cgf.14195  

   Rathore, Archit; Chalapathi, Nithin; Palande, Sourabh; Wang, Bei (January 2021, Computer Graphics Forum)

   Abstract Deep neural networks such as GoogLeNet, ResNet, and BERT have achieved impressive performance in tasks such as image and text classification. To understand how such performance is achieved, we probe a trained deep neural network by studying neuron activations, i.e.combinations of neuron firings, at various layers of the network in response to a particular input. With a large number of inputs, we aim to obtain a global view of what neurons detect by studying their activations. In particular, we develop visualizations that show the shape of the activation space, the organizational principle behind neuron activations, and the relationships of these activations within a layer. Applying tools from topological data analysis, we presentTopoAct, a visual exploration system to study topological summaries of activation vectors. We present exploration scenarios usingTopoActthat provide valuable insights into learned representations of neural networks. We expectTopoActto give a topological perspective that enriches the current toolbox of neural network analysis, and to provide a basis for network architecture diagnosis and data anomaly detection. 

   more » « less
5. T-BFA: Targeted Bit-Flip Adversarial Weight Attack

   https://doi.org/10.1109/TPAMI.2021.3112932  

   Rakin, Adnan Siraj; He, Zhezhi; Li, Jingtao; Yao, Fan; Chakrabarti, Chaitali; Fan, Deliang (September 2021, IEEE Transactions on Pattern Analysis and Machine Intelligence)

   Traditional Deep Neural Network (DNN) security is mostly related to the well-known adversarial input example attack.Recently, another dimension of adversarial attack, namely, attack on DNN weight parameters, has been shown to be very powerful. Asa representative one, the Bit-Flip based adversarial weight Attack (BFA) injects an extremely small amount of faults into weight parameters to hijack the executing DNN function. Prior works of BFA focus on un-targeted attacks that can hack all inputs into a random output class by flipping a very small number of weight bits stored in computer memory. This paper proposes the first work oftargetedBFA based (T-BFA) adversarial weight attack on DNNs, which can intentionally mislead selected inputs to a target output class. The objective is achieved by identifying the weight bits that are highly associated with classification of a targeted output through a class-dependent weight bit searching algorithm. Our proposed T-BFA performance is successfully demonstrated on multiple DNN architectures for image classification tasks. For example, by merely flipping 27 out of 88 million weight bits of ResNet-18, our T-BFA can misclassify all the images from Hen class into Goose class (i.e., 100% attack success rate) in ImageNet dataset, while maintaining 59.35% validation accuracy. 

   more » « less