online training - 42Papers

Home

Discover

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and Machine Learning and more.Subscribe

CC BY

Machine Learning

Neural and Evolutionary Computing

Forward Propagation Through Time

Accurate online training of dynamical spiking neural networks through Forward Propagation Through Time

We show how a recently developed alternative to error-backpropagation through time (error-backpropagation through time), forwardpropagation through time (fpt), can be applied to spiking neural networks (snns).

Unlike error-backpropagation through time, fpt attempts to minimize an ongoing dynamically regularized risk on the loss.

CC BY

Neural and Evolutionary Computing

Emerging Technologies

Online Training of Spiking Recurrent Neural Networks on Memristive Substrates

Online Training of Spiking Recurrent Neural Networks with Phase-Change Memory Synapses

Spiking recurrent neural networks (rnns) are a promising tool for solving a wide variety of complex cognitive and motor tasks, due to their rich temporal dynamics and sparse processing.

However training spiking rnns on dedicated neuromorphic hardware is still an open challenge due mainly to the lack of local, hardware-friendly learning mechanisms that can solve the temporal credit assignment problem and ensure stable network dynamics, even when the weight resolution is limited.

Liked by대윤

CC BY

Information Retrieval

Monolith: A Real-Time Recommender Framework for Online Training

Monolith: Real Time Recommendation System With Collisionless Embedding Table

In this paper, we present the design and implementation of monolith, a real-time recommendation system tailored for online training.

Our design has been driven by observations of our applicationworkloads and production environment that reflects a marked departure from other recommendations systems.

Neural and Evolutionary Computing

Emerging Technologies

On-Chip Error-triggered Learning of Multi-layer Memristive Spiking Neural Networks

Recent breakthroughs in neuromorphic computing show that local forms of gradient descent learning are compatible with Spiking Neural Networks (SNNs) and synaptic plasticity. Although SNNs can be scala

More...

Machine Learning

Neural and Evolutionary Computing

Neurons and Cognition

Stats Machine Learning

A Unified Framework of Online Learning Algorithms for Training Recurrent Neural Networks

We present a framework for compactly summarizing many recent results in efficient and/or biologically plausible online training of recurrent neural networks (RNN). The framework organizes algorithms a

More...

Machine Learning

Neural and Evolutionary Computing

Neurons and Cognition

Meta-Learning Biologically Plausible Plasticity Rules with Random Feedback Pathways

Backpropagation is widely used to train artificial neural networks, but its relationship to synaptic plasticity in the brain is unknown. Some biological models of backpropagation rely on feedback proj

More...

CC BY

Computers and Society

Human-Computer Interaction

Social and Information Networks

A pilot study of an online social media literacy campaign aimed at empowering individuals in Indonesia with skills to help them identify misinformation

Pilot Study Suggests Online Media Literacy Programming Reduces Belief in False News in Indonesia

We offer a pilot study regarding the efficacy of an online social media literacy campaign aimed at empoweringindividuals in indonesia with skills to help them identify misinformation.

Amidst the threat of digital misinformation, we offer a pilot study regarding the efficacy of an online social media literacy campaign aimed at empoweringindividuals in indonesia with skills to help them identify misinformation.

CC BY

Machine Learning

Artificial Intelligence

Consistency in Dropout for Policy-Gradient Learning

Consistent Dropout for Policy Gradient Reinforcement Learning

We analyze why naive application of dropout is problematic for policy-gradient learning algorithms and introduce consistentdropout, a simple technique to address this instability.

We demonstrate consistent dropout enables stable training with a2c and ppo in both continuousand discrete action environments across a wide range of dropout probabilities across a wide range of dropout probabilities.

CC BY

Robotics

Online Deep Reinforcement Learning for Autonomous Driving

Accelerating Online Reinforcement Learning via Supervisory Safety Systems

We present a method of online training a deep reinforcement learning agent to drive autonomously on a physical vehicle by using a model-based safety supervisor.

Our solution uses a supervisory system to check if the action selected by the agent is safe or unsafe and ensure that a safe action is always implemented on the vehicle.

CC BY

Computation and Language

Self-Correction: Learning to Correct Imperfect Generation

Generating Sequences by Learning to Self-Correct

We present an approach that decouples an imperfect base generator (an off-the-shelf language model or supervised sequence-to-sequence model) from a separate corrector that learns to iteratively correct imperfect generations.

We show that self-correction improves upon the base generator in three diverse generation tasks-mathematical program synthesis, lexically-constrained generation, and toxicity control-even when the corrector is much smaller than the base generator.

Applied Physics

Random Variations in Hf$_{0.5}$Zr$_{0.5}$O$_2$ based FE-finFETs: A Synergistic Approach of Interfacial Layer Engineering and Mixed Precision Architecture to Mitigate the Implications on Deep Neural Networks

This study investigates the effects of trapping and random domain distribution-induced variations in hafnium zirconium oxide based ferroelectric field-effect transistors and their application in neuro

More...

CC BY

Machine Learning

Biological Physics

ELM: Extreme Learning Machine for fluorescence lifetime imaging microscopy

Fast fluorescence lifetime imaging analysis via extreme learning machine

We present a fast and accurate analytical method for fluorescence lifetime imaging microscopy (flim) using the extreme learning machine (elm).

We used extensive metrics to evaluate these algorithms using synthetic datasets and human prostate cancer cells loaded with gold nanosensors.

Machine Learning

Artificial Intelligence

Networking and Internet Architecture

Knowledge Transfer in Deep Reinforcement Learning for Slice-Aware Mobility Robustness Optimization

The legacy mobility robustness optimization (MRO) in self-organizing networks aims at improving handover performance by optimizing cell-specific handover parameters. However, such solutions cannot sat

More...

Human-Computer Interaction

Toward Imagined Speech based Smart Communication System: Potential Applications on Metaverse Conditions

Recently, brain-computer interface (BCI) system is aiming to provide user-friendly and intuitive means of communication. Imagined speech has become an alternative neuro-paradigm for communicative BCI

More...

Machine Learning

Artificial Intelligence

Fuzzy Tiling Activations: A Simple Approach to Learning Sparse Representations Online

Recent work has shown that sparse representations -- where only a small percentage of units are active -- can significantly reduce interference. Those works, however, relied on relatively complex regu

More...

Machine Learning

Computer Vision

Online Bag-of-Visual-Words Generation for Unsupervised Representation Learning

Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invar

More...

CC BY-SA

Machine Learning

Optimization and Control

EESS Systems and Control

Robotics

Online Reinforcement Learning with Unscented Transform

FORESEE: Model-based Reinforcement Learning using Unscented Transform with application to Tuning of Control Barrier Functions

We introduce a novel online model-based reinforcement learning algorithm that uses unscented transform to propagate uncertainty for the prediction of the future reward.

Previous approaches either approximate the state distribution at each step of the prediction horizon with a gaussian, or perform monte carlo simulations to estimate the rewards.

Home

Discover

Bookmarks

◐ Recommended Follows

◐ Latest Activity