Search Results for author:
Found 21 papers, 11 papers with code
What's In Your Field? Mapping Scientific Research with Knowledge Graphs and Large Language Models
The scientific literature's exponential growth makes it increasingly challenging to navigate and synthesize knowledge across disciplines.
Contextual Counting: A Mechanistic Study of Transformers on a Quantitative Task
Transformers have revolutionized machine learning across diverse domains, yet understanding their behavior remains crucial, particularly in high-stakes applications.
Neuronal Temporal Filters as Normal Mode Extractors
Such variation in the temporal filter with input SNR resembles that observed experimentally in biological neurons.
AstroCLIP: A Cross-Modal Foundation Model for Galaxies
These embeddings can then be used - without any model fine-tuning - for a variety of downstream tasks including (1) accurate in-modality and cross-modality semantic similarity search, (2) photometric redshift estimation, (3) galaxy property estimation from both images and spectra, and (4) morphology classification.
xVal: A Continuous Numerical Tokenization for Scientific Language Models
Due in part to their discontinuous and discrete default encodings for numbers, Large Language Models (LLMs) have not yet been commonly used to process numerically-dense scientific datasets.
Multiple Physics Pretraining for Physical Surrogate Models
We introduce multiple physics pretraining (MPP), an autoregressive task-agnostic pretraining approach for physical surrogate modeling of spatiotemporal systems with transformers.
Reusability report: Prostate cancer stratification with diverse biologically-informed neural architectures
This suggests that different neural architectures are sensitive to different aspects of the data, an important yet under-explored challenge for clinical prediction tasks.
Normative framework for deriving neural networks with multi-compartmental neurons and non-Hebbian plasticity
These NN models account for many anatomical and physiological observations; however, the objectives have limited computational power and the derived NNs do not explain multi-compartmental neuronal structures and non-Hebbian forms of plasticity that are prevalent throughout the brain.
An online algorithm for contrastive Principal Component Analysis
However, the performance of cPCA is sensitive to hyper-parameter choice and there is currently no online algorithm for implementing cPCA.
Constrained Predictive Coding as a Biologically Plausible Model of the Cortical Hierarchy
The network we derive does not involve one-to-one connectivity or signal multiplexing, which the phenomenological models required, indicating that these features are not necessary for learning in the cortex.
Neural optimal feedback control with local learning rules
This network performs system identification and Kalman filtering, without the need for multiple phases with distinct update rules or the knowledge of the noise covariances.
Neural circuits for dynamics-based segmentation of time series
In particular, the segmentation accuracy is similar to that obtained from oracle-like methods in which the ground-truth parameters of the autoregressive models are known.
A biologically plausible neural network for local supervision in cortical microcircuits
The backpropagation algorithm is an invaluable tool for training artificial neural networks; however, because of a weight sharing requirement, it does not provide a plausible model of brain function.
A biologically plausible neural network for Slow Feature Analysis
Furthermore, when trained on naturalistic stimuli, SFA reproduces interesting properties of cells in the primary visual cortex and hippocampus, suggesting that the brain uses temporal slowness as a computational principle for learning latent features.
A simple normative network approximates local non-Hebbian learning in the cortex
Here, adopting a normative approach, we model these instructive signals as supervisory inputs guiding the projection of the feedforward data.
A biologically plausible neural network for multi-channel Canonical Correlation Analysis
For biological plausibility, we require that the network operates in the online setting and its synaptic update rules are local.
Emergent Structures and Lifetime Structure Evolution in Artificial Neural Networks
These different structures can be derived using gradient descent on a single general loss function where the structure of the data and the relative strengths of various regulator terms determine the structure of the emergent network.
Task-Driven Data Verification via Gradient Descent
We introduce a novel algorithm for the detection of possible sample corruption such as mislabeled samples in a training dataset given a small clean validation set.
Inferring the quantum density matrix with machine learning
We also introduce quantum flows, the quantum analog of normalizing flows, which can be used to increase the expressivity of this variational family.
Continual Learning via Neural Pruning
We introduce Continual Learning via Neural Pruning (CLNP), a new method aimed at lifelong learning in fixed capacity models based on neuronal model sparsification.
Backdrop: Stochastic Backpropagation
We introduce backdrop, a flexible and simple-to-implement method, intuitively described as dropout acting only along the backpropagation pipeline.
