Search Results for author:
Found 25 papers, 8 papers with code
Representation Learning of Multivariate Time Series using Attention and Adversarial Training
In this work, a Transformer-based autoencoder is proposed that is regularized using an adversarial training scheme to generate artificial multivariate time series signals.
Learning Object Permanence from Videos via Latent Imaginations
While human infants exhibit knowledge about object permanence from two months of age onwards, deep-learning approaches still largely fail to recognize objects' continued existence.
Loci-Segmented: Improving Scene Segmentation Learning
Current slot-oriented approaches for compositional scene segmentation from images and videos rely on provided background information or slot assignments.
The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory
However, for a majority of deep learning approaches based on DANNs, the kernel structure of neural signal processing remains the same, where the node response is encoded as a linear superposition of neural activity, while the non-linearity is triggered by the activation functions.
Inductive biases in deep learning models for weather prediction
We show how the design choices made in each of the five design elements relate to structural assumptions.
Efficient LSTM Training with Eligibility Traces
With the help of these extensions we show that, under certain conditions, e-prop can outperform BPTT for one of the two benchmarks for supervised learning.
A Taxonomy of Recurrent Learning Rules
Backpropagation through time (BPTT) is the de facto standard for training recurrent neural networks (RNNs), but it is non-causal and non-local.
Generating Sparse Counterfactual Explanations For Multivariate Time Series
Since neural networks play an increasingly important role in critical sectors, explaining network predictions has become a key research topic.
Binding Dancers Into Attractors
Our system flexibly binds the information of the rotating figure into the alternative attractors resolving the illusion's ambiguity and imagining the respective depth interpretation and the corresponding direction of rotation.
Learning What and Where: Disentangling Location and Identity Tracking Without Supervision
Moreover, it can anticipate object motion and interactions, which are crucial abilities for conceptual planning and reasoning.
Ranked #1 on
Video Object Tracking
on CATER
Inference of Affordances and Active Motor Control in Simulated Agents
We show that our architecture, which is trained end-to-end to minimize an approximation of free energy, develops latent states that can be interpreted as affordance maps.
Composing Partial Differential Equations with Physics-Aware Neural Networks
We introduce a compositional physics-aware FInite volume Neural Network (FINN) for learning spatiotemporal advection-diffusion processes.
Early Recognition of Ball Catching Success in Clinical Trials with RNN-Based Predictive Classification
Specifically, PSC is able to confidently classify the success of catching trials as early as 123 milliseconds before the first ball contact.
Latent Event-Predictive Encodings through Counterfactual Regularization
A critical challenge for any intelligent system is to infer structure from continuous data streams.
Finite Volume Neural Network: Modeling Subsurface Contaminant Transport
To tackle this issue, we introduce a new approach called the Finite Volume Neural Network (FINN).
Compositionality as Learning Bias in Generative RNNs solves the Omniglot Challenge
One aspect of learning to learn concerns the development of compositional knowledge structures that can be flexibly recombined in a semantically meaningful manner to analogically solve related problems.
Binding and Perspective Taking as Inference in a Generative Neural Network Model
Evaluations show that the resulting gradient-based inference process solves the perspective taking and binding problem for known biological motion patterns, essentially yielding a Gestalt perception mechanism.
Active Tuning
We introduce Active Tuning, a novel paradigm for optimizing the internal dynamics of recurrent neural networks (RNNs) on the fly.
Latent State Inference in a Spatiotemporal Generative Model
Knowledge about the hidden factors that determine particular system dynamics is crucial for both explaining them and pursuing goal-directed interventions.
Inferring, Predicting, and Denoising Causal Wave Dynamics
The novel DISTributed Artificial neural Network Architecture (DISTANA) is a generative, recurrent graph convolution neural network.
Fostering Event Compression using Gated Surprise
Here, we introduce a hierarchical, surprise-gated recurrent neural network architecture, which models this process and develops compact compressions of distinct event-like contexts.
Learning Precise Spike Timings with Eligibility Traces
As a consequence, this limits in principle the inherent advantage of SNNs, that is, the potential to develop codes that rely on precise relative spike timings.
Investigating Efficient Learning and Compositionality in Generative LSTM Networks
In the past, the character challenge was only met by complex algorithms that were provided with stochastic primitives.
A Distributed Neural Network Architecture for Robust Non-Linear Spatio-Temporal Prediction
We introduce a distributed spatio-temporal artificial neural network architecture (DISTANA).
Learning, Planning, and Control in a Monolithic Neural Event Inference Architecture
We introduce REPRISE, a REtrospective and PRospective Inference SchEme, which learns temporal event-predictive models of dynamical systems.
