Zobrazeno 1 - 10
of 256
pro vyhledávání: '"Oates, Tim"'
Autor:
Alam, Mohammad Mahmudul, Oberle, Alexander, Raff, Edward, Biderman, Stella, Oates, Tim, Holt, James
Vector Symbolic Architectures (VSAs) are one approach to developing Neuro-symbolic AI, where two vectors in $\mathbb{R}^d$ are `bound' together to produce a new vector in the same space. VSAs support the commutativity and associativity of this bindin
Externí odkaz:
http://arxiv.org/abs/2410.22669
Autor:
Dixit, Prakhar, Oates, Tim
Many students struggle with math word problems (MWPs), often finding it difficult to identify key information and select the appropriate mathematical operations. Schema-based instruction (SBI) is an evidence-based strategy that helps students categor
Externí odkaz:
http://arxiv.org/abs/2410.13293
Malware detection is an interesting and valuable domain to work in because it has significant real-world impact and unique machine-learning challenges. We investigate existing long-range techniques and benchmarks and find that they're not very suitab
Externí odkaz:
http://arxiv.org/abs/2403.17978
Autor:
Hossain, Khondoker Murad, Oates, Tim
In the rapidly evolving landscape of communication and network security, the increasing reliance on deep neural networks (DNNs) and cloud services for data processing presents a significant vulnerability: the potential for backdoors that can be explo
Externí odkaz:
http://arxiv.org/abs/2403.08208
Autor:
Hossain, Khondoker Murad, Oates, Tim
As deep neural networks and the datasets used to train them get larger, the default approach to integrating them into research and commercial projects is to download a pre-trained model and fine tune it. But these models can have uncertain provenance
Externí odkaz:
http://arxiv.org/abs/2401.05432
While deep learning has enjoyed significant success in computer vision tasks over the past decade, many shortcomings still exist from a Cognitive Science (CogSci) perspective. In particular, the ability to subitize, i.e., quickly and accurately ident
Externí odkaz:
http://arxiv.org/abs/2312.15310
Differential Diagnosis (DDx) is the process of identifying the most likely medical condition among the possible pathologies through the process of elimination based on evidence. An automated process that narrows a large set of pathologies down to the
Externí odkaz:
http://arxiv.org/abs/2312.01242
Solving long-horizon, temporally-extended tasks using Reinforcement Learning (RL) is challenging, compounded by the common practice of learning without prior knowledge (or tabula rasa learning). Humans can generate and execute plans with temporally-e
Externí odkaz:
http://arxiv.org/abs/2311.05596
Autor:
Nolet, Corey J., Gala, Divye, Fender, Alex, Doijade, Mahesh, Eaton, Joe, Raff, Edward, Zedlewski, John, Rees, Brad, Oates, Tim
In this paper, we propose cuSLINK, a novel and state-of-the-art reformulation of the SLINK algorithm on the GPU which requires only $O(Nk)$ space and uses a parameter $k$ to trade off space and time. We also propose a set of novel and reusable buildi
Externí odkaz:
http://arxiv.org/abs/2306.16354
In recent years, self-attention has become the dominant paradigm for sequence modeling in a variety of domains. However, in domains with very long sequence lengths the $\mathcal{O}(T^2)$ memory and $\mathcal{O}(T^2 H)$ compute costs can make using tr
Externí odkaz:
http://arxiv.org/abs/2305.19534