Related papers: Slice or the Whole Pie? Utility Control for AI Mod…
With the widespread success of deep learning technologies, many trained deep neural network (DNN) models are now publicly available. However, directly reusing the public DNN models for new tasks often fails due to mismatching functionality…
Large pretrained diffusion models have demonstrated impressive generation capabilities and have been adapted to various downstream tasks. However, unlike Large Language Models (LLMs) that can learn multiple tasks in a single model based on…
Recently, diffusion transformers have gained wide attention with its excellent performance in text-to-image and text-to-vidoe models, emphasizing the need for transformers as backbone for diffusion models. Transformer-based models have…
With the rapid advancement in the performance of deep neural networks (DNNs), there has been significant interest in deploying and incorporating artificial intelligence (AI) systems into real-world scenarios. However, many DNNs lack the…
Activation functions play a decisive role in determining the capacity of Deep Neural Networks as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions…
This paper presents a new method for pre-training neural networks that can decrease the total training time for a neural network while maintaining the final performance, which motivates its use on deep neural networks. By partitioning the…
Deep Neural Networks (DNN) achieve human level performance in many image analytics tasks but DNNs are mostly deployed to GPU platforms that consume a considerable amount of power. New hardware platforms using lower precision arithmetic…
New algorithms called nudging induced neural networks (NINNs), to control and improve the accuracy of deep neural networks (DNNs), are introduced. The NINNs framework can be applied to almost all pre-existing DNNs, with forward propagation,…
Training neural networks to satisfy universal constraints over continuous domains poses unique challenges. Common examples include Lyapunov Neural Networks (Lyapunov NNs) and Physics-Informed Neural Networks (PINNs), where analytical…
The deep neural networks (DNNs) have been enormously successful in tasks that were hitherto in the human-only realm such as image recognition, and language translation. Owing to their success the DNNs are being explored for use in ever more…
For complex segmentation tasks, fully automatic systems are inherently limited in their achievable accuracy for extracting relevant objects. Especially in cases where only few data sets need to be processed for a highly accurate result,…
Most existing neural network-based approaches for solving stochastic optimal control problems using the associated backward dynamic programming principle rely on the ability to simulate the underlying state variables. However, in some…
A novel convolution neural network model, abbreviated NL-CNN is proposed, where nonlinear convolution is emulated in a cascade of convolution + nonlinearity layers. The code for its implementation and some trained models are made publicly…
Model-based reinforcement learning is an effective approach for controlling an unknown system. It is based on a longstanding pipeline familiar to the control community in which one performs experiments on the environment to collect a…
Standard deep neural networks (DNNs) are commonly trained in an end-to-end fashion for specific tasks such as object recognition, face identification, or character recognition, among many examples. This specificity often leads to…
Although multi-task deep neural network (DNN) models have computation and storage benefits over individual single-task DNN models, they can be further optimized via model compression. Numerous structured pruning methods are already…
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring. As a result, an increasing number of AI-enabled…
Deep learning models have become popular in the analysis of tabular data, as they address the limitations of decision trees and enable valuable applications like semi-supervised learning, online learning, and transfer learning. However,…
Tuning machine learning models at scale, especially finding the right hyperparameter values, can be difficult and time-consuming. In addition to the computational effort required, this process also requires some ancillary efforts including…
Graph Neural Networks (GNNs) have become powerful tools for learning from graph-structured data, finding applications across diverse domains. However, as graph sizes and connectivity increase, standard GNN training methods face significant…