Recent Advances in Deep Learning: An Overview

  title={Recent Advances in Deep Learning: An Overview},
  author={Matiur Rahman Minar and Jibon Naher},
Deep Learning is one of the newest trends in Machine Learning and Artificial Intelligence research. It is also one of the most popular scientific research trends now-a-days. Deep learning methods have brought revolutionary advances in computer vision and machine learning. Every now and then, new and new deep learning techniques are being born, outperforming state-of-the-art machine learning and even existing deep learning techniques. In recent years, the world has seen many major breakthroughs… 

A Deep Feedforward Neural Network Model for Image Prediction

A deep feedforward neural network is applied to solve the regression problem due to its ability to map complicated nonlinear functions in image fusion and image reconstruction.

Evolutionary neural networks for deep learning: a review

This study conducted a systematic review of the literature on ENNs by using the PRISMA protocol and introduced the main research techniques in terms of connection weights, architecture design and learning rules, and the existing research results are summarized.

Survey on deep learning with class imbalance

Examination of existing deep learning techniques for addressing class imbalanced data finds that research in this area is very limited, that most existing work focuses on computer vision tasks with convolutional neural networks, and that the effects of big data are rarely considered.

Understanding a Deep Neural Network Based on Neural-Path Coding

This work quantifies the neural-path in which the role of a neuron was assumed to control the amount of information that can be passed through, and proposes a method for controlling the formation of a “neural-path” to build a partially understandable neural model.

Meta-level learning for the effective reduction of model search space

This study empirically confirms the intuition that there exists a relationship between the similarity of the two different tasks and the depth of network needed to fine-tune in order to achieve accuracy parable with that of a model trained from scratch.

HBONext: An Efficient Dnn for Light Edge Embedded Devices

This thesis work introduces HBONext, a mutated version of Harmonious Bottlenecks combined with a Flipped version of Inverted Residual (FIR), which outperforms the current HBONet architecture in terms of accuracy and model size miniaturization.

FDFuzz: Applying Feature Detection to Fuzz Deep Learning Systems

This work introduces FDFuzz, an automated fuzzing technique that exposes incorrect behaviors of neural networks, and demonstrates higher efficiency in generating adversarial examples and makes better use of elements in corpus.

Hessian based analysis of SGD for Deep Nets: Dynamics and Generalization

New empirical observations and theoretical results on both the optimization dynamics and generalization behavior of SGD for deep nets based on the Hessian of the training loss and associated quantities are presented.

Traffic Flow Forecasting using Multivariate Time-Series Deep Learning and Distributed Computing

This study built several univariate and multivariate time series models including LSTM, TCN, Seq2Seq, NBeats, ARIMA and Prophet using distributed deep learning to deal with the traffic flow prediction problem.



Recent advances in convolutional neural networks

Deep learning in neural networks: An overview

On the Origin of Deep Learning

This paper primarily focuses on the precedents of the models above, examining how the initial ideas are assembled to construct the early models and how these preliminary models are developed into their current forms.

Deep Learning: A Critical Appraisal

Ten concerns for deep learning are presented, and it is suggested that deep learning must be supplemented by other techniques if the authors are to reach artificial general intelligence.

An Overview of Deep-Structured Learning for Information Processing

This paper develops a classificatory scheme to analyze and summarize major work reported in the deep learning literature, and provides a taxonomy-oriented survey on the existing deep architectures, and categorize them into three types: generative, discriminative, and hybrid.

Deep Learning of Representations: Looking Forward

This paper proposes to examine some of the challenges of scaling deep learning algorithms to much larger models and datasets, reducing optimization difficulties due to ill-conditioning or local minima, designing more efficient and powerful inference and sampling procedures, and learning to disentangle the factors of variation underlying the observed data.

Deep learning in remote sensing: a review

The challenges of using deep learning for remote sensing data analysis are analyzed, the recent advances are reviewed, and resources are provided to make deep learning in remote sensing ridiculously simple to start with.

Recent Trends in Deep Learning Based Natural Language Processing [Review Article]

This paper reviews significant deep learning related models and methods that have been employed for numerous NLP tasks and provides a walk-through of their evolution.

Representation Learning: A Review and New Perspectives

Recent work in the area of unsupervised feature learning and deep learning is reviewed, covering advances in probabilistic models, autoencoders, manifold learning, and deep networks.

Deep Learning of Representations

This chapter reviews the main motivations and ideas behind deep learning algorithms and their representation-learning components, as well as recent results, and proposes a vision of challenges and hopes on the road ahead, focusing on the questions of invariance and disentangling.