Related papers: Dimension Agnostic Neural Processes
Meta learning recently has been heavily researched and helped advance the contemporary machine learning. However, achieving well-performing meta-learning model requires a large amount of training tasks with high-quality meta-data…
Deep neural networks (DNN) have an impressive ability to invert very complex models, i.e. to learn the generative parameters from a model's output. Once trained, the forward pass of a DNN is often much faster than traditional,…
This paper presents a new neural network (NN) paradigm for scalable and generalizable stability analysis of power systems. The paradigm consists of two parts: the neural stability descriptor and the sample-augmented iterative training…
Meta-learning, or "learning to learn", refers to techniques that infer an inductive bias from data corresponding to multiple related tasks with the goal of improving the sample efficiency for new, previously unobserved, tasks. A key…
In-context learning enables transformer models to generalize to new tasks based solely on input prompts, without any need for weight updates. However, existing training paradigms typically rely on large, unstructured datasets that are…
Gradient-based meta-learning methods leverage gradient descent to learn the commonalities among various tasks. While previous such methods have been successful in meta-learning tasks, they resort to simple gradient descent during…
Meta-learning algorithms enable rapid adaptation to new tasks with minimal data, a critical capability for real-world robotic systems. This paper evaluates Model-Agnostic Meta-Learning (MAML) combined with Trust Region Policy Optimization…
Prediction-based approaches are widely used in neural architecture search (NAS), where a predictor estimates the performance of candidate architectures to guide selection. However, existing predictors are typically trained via supervised…
Coherent imaging through scatter is a challenging task in computational imaging. Both model-based and data-driven approaches have been explored to solve the inverse scattering problem. In our previous work, we have shown that a deep…
One of the fundamental limitations of Deep Neural Networks (DNN) is its inability to acquire and accumulate new cognitive capabilities. When some new data appears, such as new object classes that are not in the prescribed set of objects…
Sharpness-aware minimization (SAM) has been instrumental in improving deep neural network training by minimizing both the training loss and the sharpness of the loss landscape, leading the model into flatter minima that are associated with…
Current deep learning models for dynamics forecasting struggle with generalization. They can only forecast in a specific domain and fail when applied to systems with different parameters, external forces, or boundary conditions. We propose…
Deep Neural Networks (DNNs) are universal function approximators providing state-of- the-art solutions on wide range of applications. Common perceptual tasks such as speech recognition, image classification, and object tracking are now…
Neurons in real brains are enormously complex computational units. Among other things, they're responsible for transforming inbound electro-chemical vectors into outbound action potentials, updating the strengths of intermediate synapses,…
Model-Agnostic Meta-Learning (MAML) has become increasingly popular for training models that can quickly adapt to new tasks via one or few stochastic gradient descent steps. However, the MAML objective is significantly more difficult to…
Normalization techniques are a boon for modern deep learning. They let weights converge more quickly with often better generalization performances. It has been argued that the normalization-induced scale invariance among the weights…
Many meta-learning algorithms can be formulated into an interleaved process, in the sense that task-specific predictors are learned during inner-task adaptation and meta-parameters are updated during meta-update. The normal meta-training…
The measure of a machine learning algorithm is the difficulty of the tasks it can perform, and sufficiently difficult tasks are critical drivers of strong machine learning models. However, quantifying the generalization difficulty of…
Model Agnostic Meta-Learning (MAML) consists of two optimization loops: the outer loop learns a meta-initialization of model parameters that is shared across tasks, and the inner loop task-specific adaptation step. A variant of MAML,…
Deep learning (DL) has been applied extensively in many computational imaging problems, often leading to superior performance over traditional iterative approaches. However, two important questions remain largely unanswered: first, how well…