Proposes parameterless GOMEA and CGOMEA leveraging conditional dependencies, outperforming DSMGA-II in complex black-box problems.

Arkadiy Dushatskiy, Marco Virgolin, Anton Bouter et al.

NSA (Negative Selection Algorithm) excels in nonlinear high-dimensional anomaly detection, outperforming traditional models in accuracy and speed.

Kishor Datta Gupta, Dipankar Dasgupta

SEW ResNet enables residual learning in deep SNNs, improving accuracy and time-steps.

Wei Fang, Zhaofei Yu, Yanqi Chen et al.

DIET-SNN optimizes membrane leak and threshold for low-latency, efficient deep SNNs, achieving 69% accuracy on ImageNet.

Nitin Rathi, Kaushik Roy

Derived a spike-time-based learning rule for LIF neurons enabling error backpropagation, validated on BrainScaleS-2 with 97.1% accuracy on MNIST.

Julian Göltz, Laura Kriener, Andreas Baumbach et al.

Introduces spike-based speech datasets using physiology-inspired audio-to-spike conversion, demonstrating the importance of spike timing for classification accuracy.

Benjamin Cramer, Yannik Stradmann, Johannes Schemmel et al.

Using three GP algorithms and random search, constructing two compact features achieves comparable or superior performance to full feature sets across 21 datasets, with GP-GOMEA showing best results.

Marco Virgolin, Tanja Alderliesten, Peter A. N. Bosman

Using bit extraction, ReLU networks achieve r/d<p≤2r/d; fixed width is nearly optimal, while periodic activations yield near-exponential rates.

Dmitry Yarotsky, Anton Zhevnerchuk

POET jointly evolves environments and agents, enabling endless creation of complex challenges and solutions, with transfer mechanisms boosting innovation.

Rui Wang, Joel Lehman, Jeff Clune et al.

Proposes a style-based GAN generator with AdaIN for disentangling high-level attributes and details, achieving 43% FID improvement on FFHQ.

Tero Karras, Samuli Laine, Timo Aila

Proposed neuron normalization and direct learning algorithm, achieving high-performance SNNs on CIFAR10.

Yujie Wu, Lei Deng, Guoqi Li et al.

SLAYER method addresses non-differentiability in SNNs, achieving state-of-the-art performance on MNIST and other datasets.

Sumit Bam Shrestha, Garrick Orchard

Incorporating inequity aversion into multi-agent reinforcement learning enhances cooperation in intertemporal social dilemmas.

Edward Hughes, Joel Z. Leibo, Matthew G. Phillips et al.

Proposes regularized evolution to discover architectures surpassing human designs, achieving 83.9% top-1 ImageNet accuracy.

Esteban Real, Alok Aggarwal, Yanping Huang et al.

Submanifold Sparse Convolutional Networks maintain sparsity while achieving state-of-the-art performance with 50% less computation.

Benjamin Graham, Laurens van der Maaten

Training deep spiking neural networks on BrainScaleS wafer-scale hardware using in-the-loop backpropagation, achieving ~95% accuracy from initial 72%.

Sebastian Schmitt, Johann Klaehn, Guillaume Bellec et al.

Differentiable physics engine enables gradient-based optimization of robot controllers, significantly improving training speed and scalability.

Jonas Degrave, Michiel Hermans, Joni Dambre et al.

Introduced self-ensembling method, reducing SVHN error rate from 18.44% to 7.05%.

Samuli Laine, Timo Aila

Detect misclassified and out-of-distribution examples in neural networks using softmax probabilities, enhancing detection accuracy.

Dan Hendrycks, Kevin Gimpel

Proposes DoReFa-Net, low-bitwidth weights, activations, and gradients, achieving 46.1% top-1 accuracy on ImageNet with 1-bit weights and 2-bit activations.

Shuchang Zhou, Yuxin Wu, Zekun Ni et al.