Related papers: A Trillion Genetic Programming Instructions per Se…
We extend recent 256 SSE vector work to 512 AVX giving a four fold speedup. We use MAGPIE (Machine Automated General Performance Improvement via Evolution of software) to speedup a C++ linear genetic programming interpreter. Local search is…
Predictive coding networks are neural models that perform inference through an iterative energy minimization process, whose operations are local in space and time. While effective in shallow architectures, they suffer significant…
Reinforcement learning augmented by the representational power of deep neural networks, has shown promising results on high-dimensional problems, such as game playing and robotic control. However, the sequential nature of these problems…
The optimization of the transpose convolution layer for deep learning applications is achieved with the kernel segregation mechanism. However, kernel segregation has disadvantages, such as computing extra elements to obtain the output…
In this work, we propose FFDP, a set of IO-aware non-GEMM fused kernels supplemented with a distributed framework for image registration at unprecedented scales. Image registration is an inverse problem fundamental to biomedical and life…
Neural network training is inherently sequential where the layers finish the forward propagation in succession, followed by the calculation and back-propagation of gradients (based on a loss function) starting from the last layer. The…
Deep learning is a technique for machine learning using multi-layer neural networks. It has been used for image synthesis and image recognition, but in recent years, it has also been used for various social detection and social labeling. In…
Information theoretic analysis of large evolved programs produced by running genetic programming for up to a million generations has shown even functions as smooth and well behaved as floating point addition and multiplication loose entropy…
Deep convolutional neural networks (ConvNets) of 3-dimensional kernels allow joint modeling of spatiotemporal features. These networks have improved performance of video and volumetric image analysis, but have been limited in size due to…
Genetic fitness optimization using small populations or small population updates across generations generally suffers from randomly diverging evolutions. We propose a notion of highly probable fitness optimization through feasible…
The deployment of deep learning inference in production environments continues to grow, where throughput, latency, and hardware efficiency are critical. Although specialized accelerators are increasingly adopted, many inference workloads…
Current AI code generation systems suffer from significant latency bottlenecks due to CPU-GPU data transfers during compilation, execution, and testing phases. We establish theoretical foundations for three complementary approaches to…
Self-adaptation solutions need to periodically monitor, reason about, and adapt a running system. The adaptation step involves generating an adaptation strategy and applying it to the running system whenever an anomaly arises. In this…
Graphics Processing Units (GPUs) support dynamic voltage and frequency scaling (DVFS) in order to balance computational performance and energy consumption. However, there still lacks simple and accurate performance estimation of a given GPU…
Current connectionist simulations require huge computational resources. We describe a neural network simulator for the IBM GF11, an experimental SIMD machine with 566 processors and a peak arithmetic performance of 11 Gigaflops. We present…
Accurate prediction with multimodal data-encompassing tabular, textual, and visual inputs or outputs-is fundamental to advancing analytics in diverse application domains. Traditional approaches often struggle to integrate heterogeneous data…
The computational complexity analysis of genetic programming (GP) has been started recently by analyzing simple (1+1) GP algorithms for the problems ORDER and MAJORITY. In this paper, we study how taking the complexity as an additional…
Gaussian processes (GPs) are flexible non-parametric models, with a capacity that grows with the available data. However, computational constraints with standard inference procedures have limited exact GPs to problems with fewer than about…
Convolutional Neural Networks are extensively used in a wide range of applications, commonly including computer vision tasks like image and video classification, recognition, and segmentation. Recent research results demonstrate that…
Integrating population genetics into community ecology theory is a major goal in ecology and evolution, but analyzing the resulting models is computationally daunting. Here we describe sPEGG ($\underline{\textrm{s}}\textrm{imulating}$…