An information-theoretic perspective on intrinsic motivation in reinforcement learning: A survey
The reinforcement learning (RL) research area is very active, with an important number of
new contributions, especially considering the emergent field of deep RL (DRL). However, a …
new contributions, especially considering the emergent field of deep RL (DRL). However, a …
Entropy as a measure of variability and stemness in single-cell transcriptomics
O Gandrillon, M Gaillard, T Espinasse… - Current Opinion in …, 2021 - Elsevier
Entropy as a measure of variability and stemness in single-cell transcriptomics -
ScienceDirect Skip to main contentSkip to article Elsevier logo Journals & Books Search …
ScienceDirect Skip to main contentSkip to article Elsevier logo Journals & Books Search …
Demystifying Fixed -Nearest Neighbor Information Estimators
Estimating mutual information from independent identically distributed samples drawn from
an unknown joint density function is a basic statistical problem of broad interest with …
an unknown joint density function is a basic statistical problem of broad interest with …
A Markovian model-driven deep learning framework for massive MIMO CSI feedback
Z Liu, M del Rosario, Z Ding - IEEE Transactions on Wireless …, 2021 - ieeexplore.ieee.org
Channel state information (CSI) plays a vital role in scheduling and capacity-approaching
transmission optimization of massive MIMO communication systems. In frequency division …
transmission optimization of massive MIMO communication systems. In frequency division …
DiversityGAN: Diversity-aware vehicle motion prediction via latent semantic sampling
Vehicle trajectory prediction is crucial for autonomous driving and advanced driver assistant
systems. While existing approaches may sample from a predicted distribution of vehicle …
systems. While existing approaches may sample from a predicted distribution of vehicle …
A mixture of surprises for unsupervised reinforcement learning
Unsupervised reinforcement learning aims at learning a generalist policy in a reward-free
manner for fast adaptation to downstream tasks. Most of the existing methods propose to …
manner for fast adaptation to downstream tasks. Most of the existing methods propose to …
How does weight correlation affect generalisation ability of deep neural networks?
This paper studies the novel concept of weight correlation in deep neural networks and
discusses its impact on the networks' generalisation ability. For fully-connected layers, the …
discusses its impact on the networks' generalisation ability. For fully-connected layers, the …
Dual-Polarization Non-Linear Frequency-Division Multiplexed Transmission With -Modulation
There has been much interest in the non-linear frequency-division multiplexing (NFDM)
transmission scheme in the optical fiber communication system. Up to date, most of the …
transmission scheme in the optical fiber communication system. Up to date, most of the …
[HTML][HTML] Estimate the limit of predictability in short-term traffic forecasting: An entropy-based approach
Accurate short-term traffic forecasting is the cornerstone for Intelligent Transportation
Systems. In the past several decades, many models have been proposed to continuously …
Systems. In the past several decades, many models have been proposed to continuously …
[HTML][HTML] Power shift and connectivity changes in healthy aging during resting-state EEG
The neural activity of human brain changes in healthy individuals during aging. The most
frequent variation in patterns of neural activity are a shift from posterior to anterior areas and …
frequent variation in patterns of neural activity are a shift from posterior to anterior areas and …