Decebal Constantin Mocanu

research

∙ 08/28/2023

Continual Learning with Dynamic Sparse Training: Exploring Algorithms for Effective Model Updates

Continual learning (CL) refers to the ability of an intelligent system t...

0 Murat Onur Yildirim, et al. ∙

research

∙ 06/21/2023

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

Dynamic Sparse Training (DST) is a rapidly evolving area of research tha...

0 Aleksandra I. Nowak, et al. ∙

research

∙ 03/10/2023

Supervised Feature Selection with Neuron Evolution in Sparse Neural Networks

Feature selection that selects an informative subset of variables from d...

2 Zahra Atashgahi, et al. ∙

research

∙ 02/13/2023

Automatic Noise Filtering with Dynamic Sparse Training in Deep Reinforcement Learning

Tomorrow's robots will need to distinguish useful information from noise...

6 Bram Grooten, et al. ∙

research

∙ 12/19/2022

Dynamic Sparse Network for Time Series Classification: Learning What to "see”

The receptive field (RF), which determines the region of time series to ...

7 Qiao Xiao, et al. ∙

research

∙ 11/28/2022

You Can Have Better Graph Neural Networks by Not Training Weights at All: Finding Untrained GNNs Tickets

Recent works have impressively demonstrated that there exists a subnetwo...

12 Tianjin Huang, et al. ∙

research

∙ 11/26/2022

Where to Pay Attention in Sparse Training for Feature Selection?

A new line of research for feature selection based on neural networks ha...

23 Ghada Sokar, et al. ∙

research

∙ 07/08/2022

Memory-free Online Change-point Detection: A Novel Neural Network Approach

Change-point detection (CPD), which detects abrupt changes in the data d...

9 Zahra Atashgahi, et al. ∙

research

∙ 05/30/2022

Superposing Many Tickets into One: A Performance Booster for Sparse Neural Network Training

Recent works on sparse neural network training (sparse training) have sh...

0 Lu Yin, et al. ∙

research

∙ 02/05/2022

The Unreasonable Effectiveness of Random Pruning: Return of the Most Naive Baseline for Sparse Training

Random pruning is arguably the most naive way to attain sparsity in neur...

7 Shiwei Liu, et al. ∙

research

∙ 10/11/2021

Addressing the Stability-Plasticity Dilemma via Knowledge-Aware Continual Learning

Continual learning agents should incrementally learn a sequence of tasks...

5 Ghada Sokar, et al. ∙

research

∙ 06/28/2021

FreeTickets: Accurate, Robust and Efficient Deep Ensemble by Training with Dynamic Sparsity

Recent works on sparse neural networks have demonstrated that it is poss...

16 Shiwei Liu, et al. ∙

research

∙ 06/19/2021

Sparse Training via Boosting Pruning Plasticity with Neuroregeneration

Works on lottery ticket hypothesis (LTH) and single-shot network pruning...

5 Shiwei Liu, et al. ∙

research

∙ 06/08/2021

Dynamic Sparse Training for Deep Reinforcement Learning

Deep reinforcement learning has achieved significant success in many dec...

39 Ghada Sokar, et al. ∙

research

∙ 03/02/2021

Sparse Training Theory for Scalable and Efficient Agents

A fundamental task for artificial intelligence is learning. Deep Neural ...

0 Decebal Constantin Mocanu, et al. ∙

research

∙ 02/04/2021

Do We Actually Need Dense Over-Parameterization? In-Time Over-Parameterization in Sparse Training

In this paper, we introduce a new perspective on training deep neural ne...

10 Shiwei Liu, et al. ∙

research

∙ 02/02/2021

Truly Sparse Neural Networks at Scale

Recently, sparse training methods have started to be established as a de...

0 Selima Curci, et al. ∙

research

∙ 01/28/2021

Self-Attention Meta-Learner for Continual Learning

Continual learning aims to provide intelligent agents capable of learnin...

11 Ghada Sokar, et al. ∙

research

∙ 01/22/2021

Selfish Sparse RNN Training

Sparse neural networks have been widely applied to reduce the necessary ...

11 Shiwei Liu, et al. ∙

research

∙ 01/15/2021

Learning Invariant Representation for Continual Learning

Continual learning aims to provide intelligent agents that are capable o...

10 Ghada Sokar, et al. ∙

research

∙ 12/01/2020

Quick and Robust Feature Selection: the Strength of Energy-efficient Sparse Training for Autoencoders

Major complications arise from the recent increase in the amount of high...

5 Zahra Atashgahi, et al. ∙

research

∙ 07/15/2020

SpaceNet: Make Free Space For Continual Learning

The continual learning (CL) paradigm aims to enable neural networks to l...

15 Ghada Sokar, et al. ∙

research

∙ 06/24/2020

Topological Insights in Sparse Neural Networks

Sparse neural networks are effective approaches to reduce the resource r...

24 Shiwei Liu, et al. ∙

research

∙ 02/10/2020

Novelty Producing Synaptic Plasticity

A learning process with the plasticity property often requires reinforce...

0 Anil Yaman, et al. ∙

research

∙ 06/27/2019

On improving deep learning generalization with adaptive sparse connectivity

Large neural networks are very successful in various tasks. However, wit...

0 Shiwei Liu, et al. ∙

research

∙ 04/02/2019

Evolving Plasticity for Autonomous Learning under Changing Environmental Conditions

A fundamental aspect of learning in biological neural networks (BNNs) is...

0 Anil Yaman, et al. ∙

research

∙ 03/22/2019

Learning with Delayed Synaptic Plasticity

The plasticity property of biological neural networks allows them to per...

12 Anil Yaman, et al. ∙

research

∙ 03/17/2019

Evolving and Understanding Sparse Deep Neural Networks using Cosine Similarity

Training sparse neural networks with adaptive connectivity is an active ...

0 Joost Pieterse, et al. ∙

research

∙ 01/26/2019

Intrinsically Sparse Long Short-Term Memory Networks

Long Short-Term Memory (LSTM) has achieved state-of-the-art performances...

0 Shiwei Liu, et al. ∙

research

∙ 01/26/2019

Sparse evolutionary Deep Learning with over one million artificial neurons on commodity hardware

Microarray gene expression has widely attracted the eyes of the public a...

8 Shiwei Liu, et al. ∙

research

∙ 04/19/2018

Limited Evaluation Cooperative Co-evolutionary Differential Evolution for Large-scale Neuroevolution

Many real-world control and classification tasks involve a large number ...

0 Anil Yaman, et al. ∙

research

∙ 04/18/2018

One-Shot Learning using Mixture of Variational Autoencoders: a Generalization Learning approach

Deep learning, even if it is very successful nowadays, traditionally nee...

0 Decebal Constantin Mocanu, et al. ∙

research

∙ 07/18/2017

On-line Building Energy Optimization using Deep Reinforcement Learning

Unprecedented high volumes of data are becoming available with the growt...

0 Elena Mocanu, et al. ∙

research

∙ 07/15/2017

Evolutionary Training of Sparse Artificial Neural Networks: A Network Science Perspective

Through the success of deep learning, Artificial Neural Networks (ANNs) ...

0 Decebal Constantin Mocanu, et al. ∙

research

∙ 10/18/2016

Online Contrastive Divergence with Generative Replay: Experience Replay without Storing Data

Conceived in the early 1990s, Experience Replay (ER) has been shown to b...

0 Decebal Constantin Mocanu, et al. ∙

research

∙ 04/20/2016

A topological insight into restricted Boltzmann machines

Restricted Boltzmann Machines (RBMs) and models derived from them have b...

0 Decebal Constantin Mocanu, et al. ∙

research

∙ 04/20/2016

Estimating 3D Trajectories from 2D Projections via Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machines

Estimation, recognition, and near-future prediction of 3D trajectories b...

0 Decebal Constantin Mocanu, et al. ∙

Decebal Constantin Mocanu

Featured Co-authors