Related papers: Occam's Razor and Bender and Koller's Octopus
We introduce a new class of adaptive non-linear autoregressive (Nlar) models incorporating the concept of momentum, which dynamically estimate both the learning rates and momentum as the number of iterations increases. In our method, the…
Neural network has been recognized with its accomplishments on tackling various natural language understanding (NLU) tasks. Methods have been developed to train a robust model to handle multiple tasks to gain a general representation of…
Online Learning to Rank (OL2R) eliminates the need of explicit relevance annotation by directly optimizing the rankers from their interactions with users. However, the required exploration drives it away from successful practices in offline…
We study Socially Unacceptable Discourse (SUD) characterization and detection in online text. We first build and present a novel corpus that contains a large variety of manually annotated texts from different online sources used so far in…
Engaging students with well-designed clicker questions is one of the commonly used research-based instructional strategy in physics courses partly because it has a relatively low barrier to implementation [1]. Moreover, validated robust…
This paper studies the task of best counter-argument retrieval given an input argument. Following the definition that the best counter-argument addresses the same aspects as the input argument while having the opposite stance, we aim to…
Motivated by the recent success of end-to-end training of communications in the wireless domain, we strive to adapt the end-to-end-learning idea from the wireless case (i.e., linear) to coherent optical fiber links (i.e., nonlinear).…
We investigate the fundamental problem of leveraging offline data to accelerate online reinforcement learning - a direction with strong potential but limited theoretical grounding. Our study centers on how to learn and apply value envelopes…
We propose a discussion of angular momentum and its Euler equation, with the aim of giving a short outline of their history. This outline can be useful for teaching purposes too, to amend some problems that students can have in learning…
Newcomers to ACL2 are sometimes surprised that ACL2 rejects formulas that they believe should be theorems, such as (REVERSE (REVERSE X)) = X. Experienced ACL2 users will recognize that the theorem only holds for intended values of X, and…
Numerous recent studies have shown that Large Language Models (LLMs) are biased towards a Western and Anglo-centric worldview, which compromises their usefulness in non-Western cultural settings. However, "culture" is a complex,…
Machine learning (ML) has transformed numerous fields, but understanding its foundational research is crucial for its continued progress. This paper presents an overview of the significant classical ML algorithms and examines the…
Characterizing the content of a technical document in terms of its learning utility can be useful for applications related to education, such as generating reading lists from large collections of documents. We refer to this learning utility…
Answering complex queries over incomplete knowledge graphs (KGs) is a challenging job. Most previous works have focused on learning entity/relation embeddings and simulating first-order logic operators with various neural networks. However,…
Current status of Top/QCD studies at linear colliders (LC) is briefly viewed, classifying topics into two categories: those within the standard model and those beyond the standard model.
This thesis tackles the problem of learning efficient representations of complex, structured data with a natural application to web page and element classification. We hypothesise that the context around the element inside the web page is…
The so-called block-term decomposition (BTD) tensor model, especially in its rank-$(L_r,L_r,1)$ version, has been recently receiving increasing attention due to its enhanced ability of representing systems and signals that are composed of…
Two of the most fundamental challenges in Natural Language Understanding (NLU) at present are: (a) how to establish whether deep learning-based models score highly on NLU benchmarks for the 'right' reasons; and (b) to understand what those…
Human skeleton point clouds are commonly used to automatically classify and predict the behaviour of others. In this paper, we use a contrastive self-supervised learning method, SimCLR, to learn representations that capture the semantics of…
We build and analyze the network of hundred top cited nodes (research papers and books from Google Scholar; strength or citation of the nodes range from about 44000 up to 100) starting early 1980 to till last year. These searched…