Search Results for author:
Found 18 papers, 6 papers with code
When in Doubt, Think Slow: Iterative Reasoning with Latent Imagination
In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model.
Sample as You Infer: Predictive Coding With Langevin Dynamics
We present a novel algorithm for parameter learning in generic deep generative models that builds upon the predictive coding (PC) framework of computational neuroscience.
Weakly-Supervised Action Localization by Hierarchically-structured Latent Attention Modeling
To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics.
Automotive Object Detection via Learning Sparse Events by Spiking Neurons
Traditional object detection techniques that utilize Artificial Neural Networks (ANNs) face challenges due to the sparse and asynchronous nature of the events these sensors capture.
Cross-Inferential Networks for Source-free Unsupervised Domain Adaptation
Our main idea is that, when we adapt the network model to predict the sample labels from encoded features, we use these prediction results to construct new training samples with derived labels to learn a new examiner network that performs a different but compatible task in the target domain.
Accurate and Efficient Event-based Semantic Segmentation Using Adaptive Spiking Encoder-Decoder Network
Leveraging the low-power, event-driven computation and the inherent temporal dynamics, spiking neural networks (SNNs) are potentially ideal solutions for processing dynamic and asynchronous signals from event-based sensors.
Predictive Coding as a Neuromorphic Alternative to Backpropagation: A Critical Evaluation
Backpropagation has rapidly become the workhorse credit assignment algorithm for modern deep learning methods.
Curvature-Sensitive Predictive Coding with Approximate Laplace Monte Carlo
In part, this has been due to the poor performance of models trained with PC when evaluated by both sample quality and marginal likelihood.
Neuro-Modulated Hebbian Learning for Fully Test-Time Adaptation
We observe that the performance of this feed-forward Hebbian learning for fully test-time adaptation can be significantly improved by incorporating a feedback neuro-modulation layer.
Long-horizon video prediction using a dynamic latent hierarchy
The task of video prediction and generation is known to be notoriously difficult, with the research in this area largely limited to short-term predictions.
Self-Supervised Learning Through Efference Copies
Specifically, the brain also transforms the environment through efference, i. e. motor commands, however it sends to itself an EC of the full commands, i. e. more than a mere SSL sign.
Hebbian Deep Learning Without Feedback
Recent approximations to backpropagation (BP) have mitigated many of BP's computational inefficiencies and incompatibilities with biology, but important limitations still remain.
Modelling non-reinforced preferences using selective attention
These memories are selectively attended to, using attention and gating blocks, to update agent's preferences.
Short-Term Plasticity Neurons Learning to Learn and Forget
Its key mechanism is that synapses have a state, propagated through time by a self-recurrent connection-within-the-synapse.
Discrete Time Convolution for Fast Event-Based Stereo
Inspired by continuous dynamics of biological neuron models, we propose a novel encoding method for sparse events - continuous time convolution (CTC) - which learns to model the spatial feature of the data with intrinsic dynamics.
Variational Predictive Routing with Nested Subjective Timescales
Discovery and learning of an underlying spatiotemporal hierarchy in sequential data is an important topic for machine learning.
Spike-inspired Rank Coding for Fast and Accurate Recurrent Neural Networks
We demonstrate these in two toy problems of sequence classification, and in a temporally-encoded MNIST dataset where our RC model achieves 99. 19% accuracy after the first input time-step, outperforming the state of the art in temporal coding with SNNs, as well as in spoken-word classification of Google Speech Commands, outperforming non-RC-trained early inference with LSTMs.
SoftHebb: Bayesian Inference in Unsupervised Hebbian Soft Winner-Take-All Networks
All in all, Hebbian efficiency, theoretical underpinning, cross-entropy-minimization, and surprising empirical advantages, suggest that SoftHebb may inspire highly neuromorphic and radically different, but practical and advantageous learning algorithms and hardware accelerators.
