Search Results for author:
Found 9 papers, 4 papers with code
Deep Discriminative to Kernel Generative Networks for Calibrated Inference
We leveraged the fact that deep models, including both random forests and deep networks, learn internal representations which are unions of polytopes with affine activation functions to conceptualize them both as generalized partitioning rules.
Prospective Learning: Principled Extrapolation to the Future
We conjecture that certain sequences of tasks are not retrospectively learnable (in which the data distribution is fixed), but are prospectively learnable (in which distributions may be dynamic), suggesting that prospective learning is more difficult in kind than retrospective learning.
Simplest Streaming Trees
On three standard datasets, we illustrate that our approach, Stream Decision Forest (SDF), does not suffer from either of the aforementioned limitations.
Towards a theory of out-of-distribution learning
This assumption renders these theories inadequate for characterizing 21$^{st}$ century real world data problems, which are typically characterized by evaluation distributions that differ from the training data distributions (referred to as out-of-distribution learning).
When are Deep Networks really better than Decision Forests at small sample sizes, and how?
Empirically, we compare these two strategies on hundreds of tabular data settings, as well as several vision and auditory settings.
Omnidirectional Transfer for Quasilinear Lifelong Learning
But striving to avoid forgetting sets the goal unnecessarily low: the goal of lifelong learning, whether biological or artificial, should be to improve performance on all tasks (including past and future) with any new data.
Multiframe-based Adaptive Despeckling Algorithm for Ultrasound B-mode Imaging with Superior Edge and Texture
In this paper, we propose a multiframe-based adaptive despeckling (MADS) algorithm to reconstruct a high-resolution B-mode image from raw radio-frequency (RF) data that is based on a multiple input single output (MISO) model.
Location Forensics of Media Recordings Utilizing Cascaded SVM and Pole-matching Classifiers
Thus, we start from the problem of classifying grids with different nominal frequencies and simplify the problem of classification in three stages based on nominal frequency, SVM and finally using PM classifier.
An Ensemble SVM-based Approach for Voice Activity Detection
Therefore, a VAD with low complexity and high accuracy is highly desirable for speech processing applications.
