# DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity Source: [DynamicGate MLP Conditional Computation via Learned Structural Dropout and Input Dependent Gating for Functional Plasticity]() Collection index: [llms.txt]() Data updated: 2026-03-19T05:00:05.030Z Authors: Yong Il Choi Published: 2026-03-17T10:54:16.000Z ## Abstract Dropout is a representative regularization technique that stochastically deactivates hidden units during training to mitigate overfitting. In contrast, standard inference executes the full network with dense computation, so its goal and mechanism differ from conditional computation, where the executed operations depend on the input. This paper organizes DynamicGate-MLP into a single framework that simultaneously satisfies both the regularization view and the conditional-computation view. Instead of a random mask, the proposed model learns gates that decide whether to use each unit (or block), suppressing unnecessary computation while implementing sample-dependent execution that concentrates computation on the parts needed for each input. To this end, we define continuous gate probabilities and, at inference time, generate a discrete execution mask from them to select an execution path. Training controls the compute budget via a penalty on expected gate usage and uses a Straight-Through Estimator (STE) to optimize the discrete mask. We evaluate DynamicGate-MLP on MNIST, CIFAR-10, Tiny-ImageNet, Speech Commands, and PBMC3k, and compare it with various MLP baselines and MoE-style variants. Compute efficiency is compared under a consistent criterion using gate activation ratios and a layerweighted relative MAC metric, rather than wall-clock latency that depends on hardware and backend kernels. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Genomics Classification on PBMC3k](): Genomics Classification; PBMC3k; Accuracy: 92.57. - [Keyword Spotting on Speech Commands (val)](): Keyword Spotting; Speech Commands (val); Accuracy: 87.39. - [Keyword Spotting on Speech Commands (test)](): Keyword Spotting; Speech Commands (test); Accuracy: 86.54. - [Image Classification on Tiny ImageNet (test) with Model Efficiency Metrics](): Image Classification; Tiny ImageNet (test); Accuracy: 2.97. - [Image Classification on MNIST (test) (Standard Accuracy)](): Image Classification; MNIST (test); Test Accuracy: 98.07. ## Original sources and implementation [Original paper]() [PDF]()