Search Results for author:
Found 15 papers, 1 papers with code
Depth Separations in Neural Networks: Separating the Dimension from the Accuracy
We prove an exponential separation between depth 2 and depth 3 neural networks, when approximating an $\mathcal{O}(1)$-Lipschitz target function to constant accuracy, with respect to a distribution with support in $[0, 1]^{d}$, assuming exponentially bounded weights.
How Many Neurons Does it Take to Approximate the Maximum?
Our depth separation results are facilitated by a new lower bound for depth 2 networks approximating the maximum function over the uniform distribution, assuming an exponential upper bound on the size of the weights.
Size and depth of monotone neural networks: interpolation and approximation
Our first result establishes that every monotone function over $[0, 1]^d$ can be approximated within arbitrarily small additive error by a depth-4 monotone network.
Size and Depth Separation in Approximating Benign Functions with Neural Networks
We show a complexity-theoretic barrier to proving such results beyond size $O(d\log^2(d))$, but also show an explicit benign function, that can be approximated with networks of size $O(d)$ and not with networks of size $o(d/\log d)$.
Tight Hardness Results for Training Depth-2 ReLU Networks
We are also able to obtain lower bounds on the running time in terms of the desired additive error $\epsilon$.
Cognitive Model Priors for Predicting Human Decisions
To solve this problem, what is needed are machine learning models with appropriate inductive biases for capturing human behavior, and larger datasets.
Predicting human decisions with behavioral theories and machine learning
Here, we introduce BEAST Gradient Boosting (BEAST-GB), a novel hybrid model that synergizes behavioral theories, specifically the model BEAST, with machine learning techniques.
gprHOG and the popularity of Histogram of Oriented Gradients (HOG) for Buried Threat Detection in Ground-Penetrating Radar
Substantial research has been devoted to the development of algorithms that automate buried threat detection (BTD) with ground penetrating radar (GPR) data, resulting in a large number of proposed algorithms.
Tiling and Stitching Segmentation Output for Remote Sensing: Basic Challenges and Recommendations
In this work we consider the application of convolutional neural networks (CNNs) for pixel-wise labeling (a. k. a., semantic segmentation) of remote sensing imagery (e. g., aerial color or hyperspectral imagery).
Segmentation Of Remote Sensing Imagery
Semantic Segmentation
A Large-Scale Multi-Institutional Evaluation of Advanced Discrimination Algorithms for Buried Threat Detection in Ground Penetrating Radar
In this work we report the results of a multi-institutional effort to develop advanced buried threat detection algorithms for a real-world GPR BTD system.
A graph-theoretic approach to multitasking
A key feature of neural network architectures is their ability to support the simultaneous interaction among large numbers of units in the learning and processing of representations.
Inference in Sparse Graphs with Pairwise Measurements and Side Information
For two-dimensional grids, our results improve over Globerson et al. (2015) by obtaining optimal recovery in the constant-height regime.
Deleting and Testing Forbidden Patterns in Multi-Dimensional Arrays
For any $\epsilon \in [0, 1]$ and any large enough pattern $P$ over any alphabet, other than a very small set of exceptional patterns, we design a tolerant tester that distinguishes between the case that the distance is at least $\epsilon$ and the case that it is at most $a_d \epsilon$, with query complexity and running time $c_d \epsilon^{-1}$, where $a_d < 1$ and $c_d$ depend only on $d$.
On the Limitation of Spectral Methods: From the Gaussian Hidden Clique Problem to Rank-One Perturbations of Gaussian Tensors
We consider the following detection problem: given a realization of asymmetric matrix $X$ of dimension $n$, distinguish between the hypothesisthat all upper triangular variables are i. i. d.
FasT-Match: Fast Affine Template Matching
Fast-Match is a fast algorithm for approximate template matching under 2D affine transformations that minimizes the Sum-of-Absolute-Differences (SAD) error measure.
