Categorical models are a natural fit for many problems. When learning the distribution of categories from samples, high-dimensionality may dilute the data. Minimax optimality is too pessimistic to remedy this issue. A serendipitously discovered estimator, absolute discounting, corrects empirical frequencies by subtracting a constant from observed categories, which it then redistributes among the unobserved. It outperforms classical estimators empirically, and has been used extensively in natural language modeling. In this paper, we rigorously explain the prowess of this estimator using less pessimistic notions. We show that (1) absolute discounting recovers classical minimax KL-risk rates, (2) it is \emph{adaptive} to an effective dimension rather than the true dimension, (3) it is strongly related to the Good-Turing estimator and inherits its \emph{competitive} properties. We use power-law distributions as the cornerstone of these results.

Most robots lack the ability to learn new objects from past experiences. To migrate a robot to a new environment one must often completely re-generate the knowledge-base that it is running with. Since in open-ended domains the set of categories to be learned is not predefined, it is not feasible to assume that one can pre-program all object categories required by robots. Therefore, autonomous robots must have the ability to continuously execute learning and recognition in a concurrent and interleaved fashion. This paper proposes an open-ended 3D object recognition system which concurrently learns both the object categories and the statistical features for encoding objects. In particular, we propose an extension of Latent Dirichlet Allocation to learn structural semantic features (i.e.

This work explores CNNs for the recognition of novel categories from few examples. Inspired by the transferability properties of CNNs, we introduce an additional unsupervised meta-training stage that exposes multiple top layer units to a large amount of unlabeled real-world images. By encouraging these units to learn diverse sets of low-density separators across the unlabeled data, we capture a more generic, richer description of the visual world, which decouples these units from ties to a specific set of categories. We propose an unsupervised margin maximization that jointly estimates compact high-density regions and infers low-density separators. The low-density separator (LDS) modules can be plugged into any or all of the top layers of a standard CNN architecture. The resulting CNNs significantly improve the performance in scene classification, fine-grained recognition, and action recognition with small training samples.

In this paper we consider the case of generative models. In particular, we investigate generative adversarial networks (GANs) in the task of learning new categories in a sequential fashion. We first show that sequential fine tuning renders the network unable to properly generate images from previous categories (i.e.

Has Trump failed to sell the Iran war to the world? Are US-Israeli attacks against Iran legal? As anticipated, it ended up being One Battle After Another's night at the 98th annual Academy Awards, with the political thriller carting away six Oscars out of a total of 13 nominations. But while Paul Thomas Anderson's magnum opus continued its march towards awards-season domination, there were moments of genuine surprise and subversion in Sunday's ceremony. Host Conan O'Brien and his fellow presenters deftly avoided mentioning President Donald Trump by name, but their barbs took direct aim at his policies since returning to office.

Empirical results show that our approach can achieve substantial improvement over the state-of-the-art baselines.

In this paper we consider the case of generativemodels. In particular,we investigate generativeadversarialnetworks (GANs) in the task of learning new categories in a sequential fashion.

This year's Bafta Games Awards nominations have been released, and the unstoppable Clair Obscur: Expedition 33 is the front-runner once again. The role-playing adventure, made by French developer Sandfall Interactive, received 12 nominations in total, including best game, best music and best narrative. Having already swept the board at several video game award ceremonies, Expedition 33 was widely expected to feature heavily in this year's Bafta list. But, in a ceremony which aims to celebrate multimillion-dollar productions and independent games made by tiny teams, there are also some surprising inclusions and omissions. Expedition 33's 12 nominations is not a record for Bafta. In 2023, God of War Ragnarok was up for 14 awards - although it lost out on best game to independent game Vampire Survivors.