The next talk of Season 11 is scheduled to October 6, 2025, 20:00GMT.
CHECK THE UPCOMING EVENTS TOWARDS THE END OF THIS PAGE!
Abstract: In this talk, I will discuss an emerging and promising sub-domain of machine intelligence research known as brain-inspired computing, which focuses on the development of algorithms for conducting credit assignment, i.e., the "blame game" that characterizes how complex adaptive systems learn from data, in a more neurobiologically-grounded fashion. This line of work draws inspiration from what is currently known about the operation of biological neurons and human brains in order to craft new neural models and learning approaches. Starting from the popular backpropagation of errors (backprop) procedure used to train modern-day deep neural networks, I will discuss its various biological criticisms and practical shortcomings to then turn towards backprop-free methodology and its historical advancements, including processes such as recirculation, local representation alignment, contrastive Hebbian learning, wake-sleep, and predictive processing.
Abstract: From a perspective of feature matching, optical flow estimation for event cameras involves identifying event correspondences by comparing feature similarity across accompanying event frames. In this talk, we introduces an effective and robust high-dimensional (HD) feature descriptor for event frames, utilizing Vector Symbolic Architectures (VSA). The topological similarity among neighboring variables within VSA contributes to the enhanced representation similarity of feature descriptors for flow-matching points, while its structured symbolic representation capacity facilitates feature fusion from both event polarities and multiple spatial scales. Based on this HD feature descriptor, we propose a novel feature matching framework for event-based optical flow, encompassing both model-based (VSA-Flow) and self-supervised learning (VSA-SM) methods. In VSA-Flow, accurate optical flow estimation validates the effectiveness of HD feature descriptors. In VSA-SM, a novel similarity maximization method based on the HD feature descriptor is proposed to learn optical flow in a self-supervised way from events alone, eliminating the need for auxiliary grayscale images. This contribution marks a significant advancement in event-based optical flow within the feature matching methodology.
Paper: https://arxiv.org/abs/2405.08300.
Abstract: Embedding tables are used by machine learning systems to work with categorical features. In modern Recommendation Systems, these tables can be very large, necessitating the development of new methods for fitting them in memory, even during training. We suggest Clustered Compositional Embeddings (CCE) which combines clustering-based compression like quantization to codebooks with dynamic methods like The Hashing Trick and Compositional Embeddings (Shi et al., 2020). Experimentally CCE achieves the best of both worlds: The high compression rate of codebook-based quantization, but *dynamically* like hashing-based methods, so it can be used during training. Theoretically, we prove that CCE is guaranteed to converge to the optimal codebook and give a tight bound for the number of iterations required.
Abstract: We advance point cloud embedding using VSA, improving the computational and memory efficiency. Existing methods, such as PointNet and KPConv, rely heavily on data-driven approaches that require extensive training to capture geometric features. These approaches, while effective in certain respects, fall short in terms of inherent robustness against environmental noise and data density fluctuations, and often require substantial computational resources. These limitations restrict their application in scenarios where speed and resource constraints are critical, such as in event camera stream processing and drone navigation.
In response, we introduce novel methodologies that utilize VSA to enhance both the efficiency and robustness of point cloud embeddings, grounded in a strong theoretical framework. We further explore the application of these advanced embeddings in event-based normal flow predictions..
Abstract 1: Distributed sparse block codes (SBCs) exhibit compact representations for encoding and manipulating symbolic data structures using fixed-width vectors. One major challenge however is to disentangle, or factorize, the distributed representation of data structures into their constituent elements without having to search through all possible combinations. This factorization becomes more challenging when SBCs vectors are noisy due to perceptual uncertainty and approximations made by modern neural networks to generate the query SBCs vectors. To address these challenges, we first propose a fast and highly accurate method for factorizing a more flexible and hence generalized form of SBCs, dubbed GSBCs. Our iterative factorizer introduces a threshold-based nonlinear activation, conditional random sampling, and an ????-based similarity metric. Its random sampling mechanism, in combination with the search in superposition, allows us to analytically determine the expected number of decoding iterations, which matches the empirical observations up to the GSBC??s bundling capacity. Secondly, the proposed factorizer maintains a high accuracy when queried by noisy product vectors generated using deep convolutional neural networks (CNNs). This facilitates its application in replacing the large fully connected layer (FCL) in CNNs, whereby C trainable class vectors, or attribute combinations, can be implicitly represented by our factorizer having F-factor codebooks, each with F??C fixed codevectors. We provide a methodology to flexibly integrate our factorizer in the classification layer of CNNs with a novel loss function. With this integration, the convolutional layers can generate a noisy product vector that our factorizer can still decode, whereby the decoded factors can have different interpretations based on downstream tasks.We demonstrate the feasibility of our method on four deep CNN architectures over CIFAR-100, ImageNet-1K, and RAVEN datasets. In all use cases, the number of parameters and operations are notably reduced compared to the FCL.
Abstract 2: We introduce the Abductive Rule Learner with Context-awareness (ARLC), a model that solves abstract reasoning tasks based on Learn-VRF. ARLC features a novel and more broadly applicable training objective for abductive reasoning, resulting in better interpretability and higher accuracy when solving Raven's progressive matrices (RPM). ARLC allows both programming domain knowledge and learning the rules underlying a data distribution. We evaluate ARLC on the I-RAVEN dataset, showcasing state-of-the-art accuracy across both in-distribution and out-of-distribution (unseen attribute-rule pairs) tests. ARLC surpasses neuro-symbolic and connectionist baselines, including large language models, despite having orders of magnitude fewer parameters. We show ARLC's robustness to post-programming training by incrementally learning from examples on top of programmed knowledge, which only improves its performance and does not result in catastrophic forgetting of the programmed solution. We validate ARLC's seamless transfer learning from a 2x2 RPM constellation to unseen constellations.
Abstract: Tsetlin machines (TMs) have been successful in several application domains, operating with high efficiency on Boolean representations of the input data. However, Booleanizing complex data structures such as sequences, graphs, images, signal spectra, chemical compounds, and natural language is not trivial. In this paper, we propose a hypervector (HV) based method for expressing arbitrarily large sets of concepts associated with any input data. Using a hyperdimensional space to build vectors drastically expands the capacity and flexibility of the TM. We demonstrate how images, chemical compounds, and natural language text are encoded according to the proposed method, and how the resulting HV-powered TM can achieve significantly higher accuracy and faster learning on well-known benchmarks. Our results open up a new research direction for TMs, namely how to expand and exploit the benefits of operating in hyperspace, including new booleanization strategies, optimization of TM inference and learning, as well as new TM applications.
Abstract: Neural networks continue to struggle with compositional generalization, and this issue is exacerbated by a lack of massive pre-training. One successful approach for developing neural systems which exhibit human-like compositional generalization is neurosymbolic techniques. However, these techniques run into the core issues that plague symbolic approaches to AI: scalability and flexibility. The reason for this failure is that at their core, hybrid neurosymbolic models perform symbolic computation and relegate the scalable and flexible neural computation to parameterizing a symbolic system. We investigate a neurosymbolic system where transformations in the network can be interpreted simultaneously as both symbolic and neural computation. We extend a unified neurosymbolic architecture called the Differentiable Tree Machine in two central ways. First, we significantly increase the model’s efficiency through the use of sparse vector representations of symbolic structures. Second, we enable its application beyond the restricted set of tree2tree problems to the more general class of seq2seq problems. The improved model retains its prior generalization capabilities and, since there is a fully neural path through the network, avoids the pitfalls of other neurosymbolic techniques that elevate symbolic computation over neural computation.
Abstract: With the increasing rate of data generated by critical systems, estimating functions on streaming data has become essential. This demand has driven numerous advancements in algorithms designed to efficiently query and analyze one or more data streams while operating under memory constraints. The primary challenge arises from the rapid influx of new items, requiring algorithms that enable efficient incremental processing of streams in order to keep up. A prominent algorithm in this domain is the AMS sketch. Originally developed to estimate the second frequency moment of a data stream, it can also estimate the cardinality of the equi-join between two relations. Since then, two important advancements are the Count sketch, a method which significantly improves upon the sketch update time, and secondly, an extension of the AMS sketch to accommodate multi-join queries. However, combining the strengths of these methods to maintain sketches for multi-join queries while ensuring fast update times is a non-trivial task, and has remained an open problem for decades as highlighted in the existing literature. In this work, we successfully address this problem by introducing a novel sketching method which has fast updates, even for sketches capable of accurately estimating the cardinality of complex multi-join queries. We prove that our estimator is unbiased and has the same error guarantees as the AMS-based method. Our experimental results confirm the significant improvement in update time complexity, resulting in orders of magnitude faster estimates, with equal or better estimation accuracy..