Related papers: Eigen Memory Trees

In this paper, we extend an attention-based neural machine translation (NMT) model by allowing it to access an entire training set of parallel sentence pairs even after training. The proposed approach consists of two stages. In the first…

Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…

In meta-learning, the knowledge learned from previous tasks is transferred to new ones, but this transfer only works if tasks are related. Sharing information between unrelated tasks might hurt performance, and it is unclear how to transfer…

Density Estimation Trees (DETs) are decision trees trained on a multivariate dataset to estimate its probability density function. While not competitive with kernel techniques in terms of accuracy, they are incredibly fast, embarrassingly…

One of the current challenges in machine learning is how to deal with data coming at increasing rates in data streams. New predictive learning strategies are needed to cope with the high throughput data and concept drift. One of the data…

Merkle tree is a widely used tree structure for authentication of data/metadata in a secure computing system. Recent state-of-the art secure systems use a smaller-sized MT, namely Bonsai Merkle Tree (BMT) to protect the metadata such as…

Large language models (LLMs) have shown remarkable capabilities, but still struggle with processing extensive contexts, limiting their ability to maintain coherence and accuracy over long sequences. In contrast, the human brain excels at…

Highly-concurrent system models with vast state spaces like Chemical Reaction Networks (CRNs) that model biological and chemical systems pose a formidable challenge to cutting-edge formal analysis tools. Although many symbolic approaches…

With the rapid growth of the scientific literature, manually selecting appropriate citations for a paper is becoming increasingly challenging and time-consuming. While several approaches for automated citation recommendation have been…

Pre-trained language models such as BERT have been a key ingredient to achieve state-of-the-art results on a variety of tasks in natural language processing and, more recently, also in information retrieval.Recent research even claims that…

Decision trees and random forest remain highly competitive for classification on medium-sized, standard datasets due to their robustness, minimal preprocessing requirements, and interpretability. However, a single tree suffers from high…

Spatial memory, or the ability to remember and recall specific locations and objects, is central to autonomous agents' ability to carry out tasks in real environments. However, most existing artificial memory modules are not very adept at…

A memory efficient approach to ensembling neural networks is to share most weights among the ensembled models by means of a single reference network. We refer to this strategy as Embedded Ensembling (EE); its particular examples are…

Online planning under uncertainty remains a critical challenge in robotics and autonomous systems. While tree search techniques are commonly employed to construct partial future trajectories within computational constraints, most existing…

We consider the problems of computing maximal palindromes and distinct palindromes in a trie. A trie is a natural generalization of a string, which can be seen as a single-path tree. There is a linear-time offline algorithm to compute…

A treap is a classic randomized binary search tree data structure that is easy to implement and supports O(\log n) expected time access. However, classic treaps do not take advantage of the input distribution or patterns in the input. Given…

Current generation of memory-augmented neural networks has limited scalability as they cannot efficiently process data that are too large to fit in the external memory storage. One example of this is lifelong learning scenario where the…

We revisit self-adjusting external memory tree data structures, which combine the optimal (and practical) worst-case I/O performances of B-trees, while adapting to the online distribution of queries. Our approach is analogous to undergoing…

This paper introduces a novel neural network model for question answering, the \emph{entity-based memory network}. It enhances neural networks' ability of representing and calculating information over a long period by keeping records of…

Combinatorial optimization (CO) underlies decision-making from logistics to chip design, where infeasible solutions are operationally unusable and small quality gains translate into substantial economic value. Recent work uses large…