4 papers
Investigating Sindy As a Tool For Causal Discovery In Time Series Signals
Andrew O'Brien, Rosina Weber, Edward Kim
The SINDy algorithm has been successfully used to identify the governing equations of dynamical systems from time series data. In this paper, we argue that this makes SINDy a poten…
Dictionary Learning with Accumulator Neurons
Gavin Parpart, Carlos Gonzalez, Terrence C. Stewart +6
The Locally Competitive Algorithm (LCA) uses local competition between non-spiking leaky integrator neurons to infer sparse representations, allowing for potentially real-time exec…
EvoSTS Forecasting: Evolutionary Sparse Time-Series Forecasting
Ethan Jacob Moyer, Alisha Isabelle Augustin, Satvik Tripathi +5
In this work, we highlight our novel evolutionary sparse time-series forecasting algorithm also known as EvoSTS. The algorithm attempts to evolutionary prioritize weights of Long S…
Perception Over Time: Temporal Dynamics for Robust Image Understanding
Maryam Daniali, Edward Kim
While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in…