Latest Research
Dropping forward-backward algorithms for feature selection
In this era of big data, feature selection techniques, which have long been proven to simplify the model, makes the model more comprehensible, speed up the process of learning, have become more and more important.
Convolutional Character Networks
• MalongTech/research-charnet
• 
We evaluate CharNet on three standard benchmarks, where it consistently outperforms the state-of-the-art approaches [25, 24] by a large margin, e. g., with improvements of 65. 33%->71. 08% (with generic lexicon) on ICDAR 2015, and 54. 0%->69. 23% on Total-Text, on end-to-end text recognition.
SOTA for Scene Text Detection on ICDAR 2015
DeepFork: Supervised Prediction of Information Diffusion in GitHub
To understand human influence, information spread and evolution of transmitted information among assorted users in GitHub, we developed a deep neural network model: DeepFork, a supervised machine learning based approach that aims to predict information diffusion in complex social networks; considering node as well as topological features.
Using a KG-Copy Network for Non-Goal Oriented Dialogues
• SmartDataAnalytics/KG-Copy_Network
•
Non-goal oriented, generative dialogue systems lack the ability to generate answers with grounded facts.
Cross Attention Network for Few-shot Classification
• Duan-JM/awesome-papers-fewshot
The unseen classes and low-data problem make few-shot classification very challenging.
Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization
• sorooshafiee/Optimistic_Likelihoods
A fundamental problem arising in many areas of machine learning is the evaluation of the likelihood of a given observation under different nominal distributions.
Meta-learning for fast classifier adaptation to new users of Signature Verification systems
• luizgh/sigver
•
This is particularly challenging for skilled forgeries, where a forger practices imitating the user's signature, and often is able to create forgeries visually close to the original signatures.
Root Mean Square Layer Normalization
• bzhangGo/rmsnorm
• 
RMSNorm regularizes the summed inputs to a neuron in one layer according to root mean square (RMS), giving the model re-scaling invariance property and implicit learning rate adaptation ability.
Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
We consider the problem of how a teacher algorithm can enable an unknown Deep Reinforcement Learning (DRL) student to become good at a skill over a wide range of diverse environments.
On Learning Paradigms for the Travelling Salesman Problem
• chaitjo/learning-paradigms-for-tsp
We explore the impact of learning paradigms on training deep neural networks for the Travelling Salesman Problem.