Search Results for author:
Found 26 papers, 4 papers with code
ProtoP-OD: Explainable Object Detection with Prototypical Parts
Interpretation and visualization of the behavior of detection transformers tends to highlight the locations in the image that the model attends to, but it provides limited insight into the \emph{semantics} that the model is focusing on.
Interpretable Brain-Inspired Representations Improve RL Performance on Visual Navigation Tasks
Visual navigation requires a whole range of capabilities.
Classification and Reconstruction Processes in Deep Predictive Coding Networks: Antagonists or Allies?
Predictive coding-inspired deep networks for visual computing integrate classification and reconstruction processes in shared intermediate layers.
Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison
These insights can inform future development of interpretable representation learning approaches for non-visual observations and advance the use of RL solutions in real-world scenarios.
A Tutorial on the Spectral Theory of Markov Chains
Markov chains are a class of probabilistic models that have achieved widespread application in the quantitative sciences.
A model of semantic completion in generative episodic memory
We assume that attention selects some part of the index matrix while others are discarded, this then represents the gist of the episode and is stored as a memory trace.
Modular Networks Prevent Catastrophic Interference in Model-Based Multi-Task Reinforcement Learning
As a remedy, enforcing an internal structure for the learned dynamics model by training isolated sub-networks for each task notably improves performance while using the same amount of parameters.
Reward prediction for representation learning and reward shaping
One of the fundamental challenges in reinforcement learning (RL) is the one of data efficiency: modern algorithms require a very large number of training samples, especially compared to humans, for solving environments with high-dimensional observations.
Singular Sturm-Liouville Problems with Zero Potential (q=0) and Singular Slow Feature Analysis
We study the special case that the potential $q$ is zero under Neumann boundary conditions and give simple and explicit criteria, solely in terms of the coefficient functions, to assess whether various properties of the regular case apply.
Latent Representation Prediction Networks
The prediction function is used as a forward model for search on a graph in a viewpoint-matching task and the representation learned to maximize predictability is found to outperform a pre-trained representation.
Laplacian Matrix for Dimensionality Reduction and Clustering
Many problems in machine learning can be expressed by means of a graph with nodes representing training samples and edges representing the relationship between samples in terms of similarity, temporal proximity, or label information.
Measuring the Data Efficiency of Deep Learning Methods
The algorithms are trained on different-sized subsets of the MNIST and Omniglot data sets.
A Hippocampus Model for Online One-Shot Storage of Pattern Sequences
To our knowledge this is the first model of the hippocampus that allows to store correlated pattern sequences online in a one-shot fashion without a consolidation process, which can instantaneously be recalled later.
Hebbian-Descent
Hebbian-descent addresses these problems by getting rid of the activation function's derivative and by centering, i. e. keeping the neural activities mean free, leading to a biologically plausible update rule that is provably convergent, does not suffer from the vanishing error term problem, can deal with correlated data, profits from seeing patterns several times, and enables successful online learning when centering is used.
Learning gradient-based ICA by neurally estimating mutual information
Several methods of estimating the mutual information of random variables have been developed in recent years.
Gradient-based Training of Slow Feature Analysis by Differentiable Approximate Whitening
We propose Power Slow Feature Analysis, a gradient-based method to extract temporally slow features from a high-dimensional input stream that varies on a faster time-scale, as a variant of Slow Feature Analysis (SFA) that allows end-to-end training of arbitrary differentiable architectures and thereby significantly extends the class of models that can effectively be used for slow feature extraction.
Global Navigation Using Predictable and Slow Feature Analysis in Multiroom Environments, Path Planning and Other Control Tasks
While PFA obtains a well predictable model, PFAx yields a model ideally suited for manipulations with predictable outcome.
PFAx: Predictable Feature Analysis to Perform Control
Features will be exclusively extracted from the main input such that they are most predictable based on themselves and the supplementary information.
Intrinsically Motivated Acquisition of Modular Slow Features for Humanoids in Continuous and Non-Stationary Environments
The former is used to make the robot self-motivated to explore by rewarding itself whenever it makes progress learning an abstraction; the later is used to update the abstraction by extracting slowly varying components from raw sensory inputs.
Graph-based Predictable Feature Analysis
We propose graph-based predictable feature analysis (GPFA), a new method for unsupervised learning of predictable features from high-dimensional time series, where high predictability is understood very generically as low variance in the distribution of the next data point given the previous ones.
Improved graph-based SFA: Information preservation complements the slowness principle
The feature space spanned by HGSFA is complex due to the composition of the nonlinearities of the nodes in the network.
Theoretical Analysis of the Optimal Free Responses of Graph-Based SFA for the Design of Training Graphs
The method is versatile, directly supports multiple labels, and provides higher accuracy compared to current graphs for the problems considered.
Gaussian-binary Restricted Boltzmann Machines on Modeling Natural Image Statistics
We present a theoretical analysis of Gaussian-binary restricted Boltzmann machines (GRBMs) from the perspective of density models.
Modeling correlations in spontaneous activity of visual cortex with centered Gaussian-binary deep Boltzmann machines
Our work demonstrates the centered GDBM is a meaningful model approach for basic receptive field properties and the emergence of spontaneous activity patterns in early cortical visual areas.
Predictable Feature Analysis
In our approach, we measure predictability with respect to a certain prediction model.
How to Center Binary Deep Boltzmann Machines
This work analyzes centered binary Restricted Boltzmann Machines (RBMs) and binary Deep Boltzmann Machines (DBMs), where centering is done by subtracting offset values from visible and hidden variables.
