Search · four archives
Search · four archives
27 papers · ranked by Valyu relevance
Nesreen K. Ahmed, Ryan A. Rossi, Rong Zhou, John Boaz Lee + 3 more
'Xiangnan Kong' 'Theodore L. Willke' 'Hoda Eldardiry'] | Nesreen K. Ahmed | | Ryan A. Rossi | Rong Zhou | | --- | --- | --- | --- | | Intel Labs | | PARC | Google | | nesreen.k.ahmed@intel.com | | rrossi@parc.com | rongzhou@google.com | | John Boaz Lee | Xiangnan Kong | Theodore L. Willke | Hoda Eldardiry | | WPI | WPI…
Hongbo Liu, Yue Chen, Peng He, Chao Zhang + 2 more
Conventional knowledge graph representation learn the representation of entities and relations by projecting triples in the knowledge graph to a continuous vector space. The vector representation increases the precision of link prediction and the efficiency of downstream tasks. However, these methods cannot process…
Karl Ridgeway
With the resurgence of interest in neural networks, representation learning has re-emerged as a central focus in artificial intelligence. Representation learning refers to the discovery of useful encodings of data that make domain-relevant information explicit. Factorial representations identify underlying independent…
Kyle Hsu, Jubayer Ibn Hamid, Kaylee Burns, Chelsea Finn + 1 more
Representation Learning Authors: ['Kyle Hsu' 'Jubayer Ibn Hamid' 'Kaylee Burns' 'Chelsea Finn' 'Jia-Jun Wu'] Inductive biases are crucial in disentangled representation learning for narrowing down an underspecified solution set. In this work, we consider endowing a neural network autoencoder with three select inductive…
Asmaul Hosna, Ethel Merry, Jigmey Gyalmo, Zulfikar Alom + 2 more
'Mohammad Abdul Azim'] Infinite numbers of real-world applications use Machine Learning (ML) techniques to develop potentially the best data available for the users. Transfer learning (TL), one of the categories under ML, has received much attention from the research communities in the past few years. Traditional ML…
Blake Bordelon, Cengiz Pehlevan
The brain can learn from a limited number of experiences, an ability which requires suitable built in assumptions about the nature of the tasks which must be learned, or inductive biases. While inductive biases are central components of intelligence, how they are reflected in and shaped by population codes are not…
Ninad Daithankar, Alexi Gladstone, Yann LeCun, Heng Ji
Progress in AI has largely been driven by methods that assume less. As compute and data increase, approaches with weaker inductive biases generally outperform those with stronger assumptions. This is particularly characteristic of the field of Visual Representation Learning, where approaches have gone from being…
Anna Székely, Balázs Török, Mariann Kiss, Karolina Janacsek + 2 more
'Dezső Németh' 'Gergő Orbán'] Title: Abstract Transfer learning, the reuse of newly acquired knowledge under novel circumstances, is a critical hallmark of human intelligence that has frequently been pitted against the capacities of artificial learning agents. Yet, the computations relevant to transfer learning have…
Eric Schulz, Joshua B. Tenenbaum, David Duvenaud, Maarten Speekenbrink + 1 more
How do people recognize and learn about complex functional structure? Taking inspiration from other areas of cognitive science, we propose that this is achieved by harnessing compositionality: complex structure is decomposed into simpler building blocks. We formalize this idea within the framework of Bayesian…
Héctor Geffner
Recent breakthroughs in AI have shown the remarkable power of deep learning and deep reinforcement learning. These developments, however, have been tied to specific tasks, and progress in out-of-distribution generalization has been limited. While it is assumed that these limitations can be overcome by incorporating…
Somnath Basu Roy Chowdhury, K M Annervaz, Ambedkar Dukkipati
Supervised learning models are typically trained on a single dataset and the performance of these models rely heavily on the size of the dataset, i.e., amount of data available with the ground truth. Learning algorithms try to generalize solely based on the data that is presented with during the training. In this work…
Ruiyi Zhang, Xaq Pitkow, Dora E Angelaki
Artificial reinforcement learning agents that perform well in training tasks typically perform worse than animals in novel tasks. We propose one reason: generalization requires modular architectures like the brain. We trained deep reinforcement learning agents using neural architectures with various degrees of…
Mayukh Das, Nandini Ramanan, Janardhan Rao Doppa, Sriraam Natarajan
We consider the problem of learning generalized first-order representations of concepts from a small number of examples. We augment an inductive logic programming learner with 2 novel contributions. First, we define a distance measure between candidate concept representations that improves the efficiency of search for…
Takeshi Haga, Hiroshi Kera, Kazuhiko Kawamoto, Stefania Perri
In this paper, we propose a sequential variational autoencoder for video disentanglement, which is a representation learning method that can be used to separately extract static and dynamic features from videos. Building sequential variational autoencoders with a two-stream architecture induces inductive bias for video…
Gianluca Bencomo, Max Gupta, Ioana Marinescu, R. Thomas McCoy + 1 more
Artificial neural networks can acquire many aspects of human knowledge from data, making them promising as models of human learning. But what those networks can learn depends upon their inductive biases – the factors other than the data that influence the solutions they discover – and the inductive biases of neural…
Ashena Gorgan Mohammadi, Manu Srinath Halvagal, Friedemann Zenke
Tracking prey or recognizing a lurking predator is as crucial for survival as anticipating their actions. To guide behavior, the brain must extract information about object identities and their dynamics from entangled sensory inputs. How it accomplishes this feat remains an open question. Predictive coding theories…
Benjamin D. Evans, Gaurav Malhotra, Jeffrey S. Bowers
Deep Convolutional Neural Networks (DNNs) have achieved superhuman accuracy on standard image classification benchmarks. Their success has reignited significant interest in their use as models of the primate visual system, bolstered by claims of their architectural and representational similarities. However, closer…
Samuel Lippl, Kenneth Kay, Greg Jensen, Vincent P. Ferrera + 1 more
Humans and animals routinely infer relations between different items or events and generalize these relations to novel combinations of items (“compositional generalization”). This allows them to respond appropriately to radically novel circumstances and is fundamental to advanced cognition. However, how learning…
Authors not listed
Early-stage drug discovery often suffers from data scarcity and out-of-distribution (OOD) shifts, which constrain the reliability of predictive models. While deep learning has advanced representation learning from molecular and biological data, tabular modeling remains indispensable, particularly in small-sample and…
Ravid Shwartz Ziv, Yann LeCun, Shuangming Yang, Shujian Yu + 3 more
'Luis Gonzalo Sánchez Giraldo' 'Badong Chen' 'Sotiris Kotsiantis'] Deep neural networks excel in supervised learning tasks but are constrained by the need for extensive labeled data. Self-supervised learning emerges as a promising alternative, allowing models to learn without explicit labels. Information theory has…
Zhe Li, Josue Ortega Caro, Evgenia Rusak, Wieland Brendel + 5 more
Machine learning models have difficulty generalizing to data outside of the distribution they were trained on. In particular, vision models are usually vulnerable to adversarial attacks or common corruptions, to which the human visual system is robust. Recent studies have found that regularizing machine learning models…
Julia H. Wang, Dexter Tsin, Tatiana A. Engel
Variational autoencoders (VAEs) have been used extensively to discover low-dimensional latent factors governing neural activity and animal behavior. However, without careful model selection, the uncovered latent factors may reflect noise in the data rather than true underlying features, rendering such representations…
Tianfan Jin, Brett M Savoie
Contemporary machine learning algorithms have largely succeeded in automating the development of mathematical models from data. Although this is a striking accomplishment, it leaves unaddressed the multitude of scenarios, especially across the chemical sciences and engineering, where deductive, rather than inductive…
Niall O’ Mahony, Sean Campbell, Lenka Krpalkova, Anderson Carvalho + 10 more
Fine-grained change detection in sensor data is very challenging for artificial intelligence though it is critically important in practice. It is the process of identifying differences in the state of an object or phenomenon where the differences are class-specific and are difficult to generalise. As a result, many…
David Buterez, Jon Paul Janet, Steven Kiddle, Pietro Liò
We investigate the potential of graph neural networks for transfer learning and improving molecular property prediction on sparse and expensive to acquire high-fidelity data by leveraging low-fidelity measurements as an inexpensive proxy for a targeted property ofinterest. This problem arises in discovery processes…
Hang Hu, Jyothsna Padmakumar Bindu, Julia Laskin
Mass spectrometry imaging (MSI) is widely used for the label-free molecular mapping of biological samples. The identification of co-localized molecules in MSI data is crucial to the understanding of biochemical pathways. However, complex MSI data are too large for manual annotation but too small for training deep…
Authors not listed
Machine learning models are increasingly applied to heterogeneous materials datasets spanning different synthesis routes, measurement protocols, and structural classes. Although multi-task and representation-learning approaches are commonly used to improve predictive performance, the latent representations learned by…