Dropping forward-backward algorithms for feature selection

17 Oct 2019thunguyen177/dfb

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.


17 Oct 2019

Convolutional Character Networks

17 Oct 2019MalongTech/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.


17 Oct 2019

DeepFork: Supervised Prediction of Information Diffusion in GitHub

17 Oct 2019akula01/DeepFork

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.


17 Oct 2019

Using a KG-Copy Network for Non-Goal Oriented Dialogues

17 Oct 2019SmartDataAnalytics/KG-Copy_Network

Non-goal oriented, generative dialogue systems lack the ability to generate answers with grounded facts.


17 Oct 2019

Cross Attention Network for Few-shot Classification

17 Oct 2019Duan-JM/awesome-papers-fewshot

The unseen classes and low-data problem make few-shot classification very challenging.

17 Oct 2019

Calculating Optimistic Likelihoods Using (Geodesically) Convex Optimization

17 Oct 2019sorooshafiee/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.

17 Oct 2019

Meta-learning for fast classifier adaptation to new users of Signature Verification systems

17 Oct 2019luizgh/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.


17 Oct 2019

Root Mean Square Layer Normalization

16 Oct 2019bzhangGo/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.

16 Oct 2019

Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments

16 Oct 2019flowersteam/teachDeepRL

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.

16 Oct 2019

On Learning Paradigms for the Travelling Salesman Problem

16 Oct 2019chaitjo/learning-paradigms-for-tsp

We explore the impact of learning paradigms on training deep neural networks for the Travelling Salesman Problem.

16 Oct 2019