Related papers: Distributed Evolution Strategies Using TPUs for Me…
Although deep reinforcement learning methods can learn effective policies for challenging problems such as Atari games and robotics tasks, algorithms are complex, and training times are often long. This study investigates how Evolution…
As neural networks are increasingly being applied to real-world applications, mechanisms to address distributional shift and sequential task learning without forgetting are critical. Methods incorporating network expansion have shown…
Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years. Existing meta-learning methods for time series prediction, which predominantly…
Training a neural network using backpropagation algorithm requires passing error gradients sequentially through the network. The backward locking prevents us from updating network layers in parallel and fully leveraging the computing…
Back-propagation algorithm is one of the most widely used and popular techniques to optimize the feed forward neural network training. Nature inspired meta-heuristic algorithms also provide derivative-free solution to optimize complex…
Though deep learning methods have shown great success in 3D point cloud part segmentation, they generally rely on a large volume of labeled training data, which makes the model suffer from unsatisfied generalization abilities to unseen…
Transfer learning is a popular practice in deep neural networks, but fine-tuning of large number of parameters is a hard task due to the complex wiring of neurons between splitting layers and imbalance distributions of data in pretrained…
Neural Processes (NPs) are a popular class of approaches for meta-learning. Similar to Gaussian Processes (GPs), NPs define distributions over functions and can estimate uncertainty in their predictions. However, unlike GPs, NPs and their…
Animals often demonstrate a remarkable ability to adapt to their environments during their lifetime. They do so partly due to the evolution of morphological and neural structures. These structures capture features of environments shared…
In meta-learning an agent extracts knowledge from observed tasks, aiming to facilitate learning of novel future tasks. Under the assumption that future tasks are 'related' to previous tasks, the accumulated knowledge should be learned in a…
The deployment of large-scale models, such as large language models (LLMs) and sophisticated image generation systems, incurs substantial costs due to their computational demands. To mitigate these costs and address challenges related to…
Recent progress in scientific machine learning (SciML) has opened up the possibility of training novel neural network architectures that solve complex partial differential equations (PDEs). Several (nearly data free) approaches have been…
Many concepts have been proposed for meta learning with neural networks (NNs), e.g., NNs that learn to reprogram fast weights, Hebbian plasticity, learned learning rules, and meta recurrent NNs. Our Variable Shared Meta Learning (VSML)…
We give the first provably efficient algorithms for learning neural networks with distribution shift. We work in the Testable Learning with Distribution Shift framework (TDS learning) of Klivans et al. (2024), where the learner receives…
We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En…
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks. However, the efficacy of meta-learning crucially depends on the distribution of tasks…
This paper proposes a novel meta-learning approach to optimize a robust portfolio ensemble. The method uses a deep generative model to generate diverse and high-quality sub-portfolios combined to form the ensemble portfolio. The generative…
Stacked unsupervised learning (SUL) seems more biologically plausible than backpropagation, because learning is local to each layer. But SUL has fallen far short of backpropagation in practical applications, undermining the idea that SUL…
The ubiquitous backpropagation algorithm requires sequential updates through the network introducing a locking problem. In addition, back-propagation relies on the transpose of forward weight matrices to compute updates, introducing a…
Majority of the modern meta-learning methods for few-shot classification tasks operate in two phases: a meta-training phase where the meta-learner learns a generic representation by solving multiple few-shot tasks sampled from a large…