Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userLearning Not to Learn: Training Deep Neural Networks with Biased Data
121
0
0.0
(
0
)
Added by
Byungju Kim
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
We propose a novel regularization algorithm to train deep neural networks, in which data at training time is severely biased. Since a neural network efficiently learns data distribution, a network is likely to learn the bias information to categorize input data. It leads to poor performance at test time, if the bias is, in fact, irrelevant to the categorization. In this paper, we formulate a regularization loss based on mutual information between feature embedding and bias. Based on the idea of minimizing this mutual information, we propose an iterative algorithm to unlearn the bias information. We employ an additional network to predict the bias distribution and train the network adversarially against the feature embedding network. At the end of learning, the bias prediction network is not able to predict the bias not because it is poorly trained, but because the feature embedding network successfully unlearns the bias information. We also demonstrate quantitative and qualitative experimental results which show that our algorithm effectively removes the bias information from feature embedding.
rate research
Read More
Learning how to act when there are many available actions in each state is a challenging task for Reinforcement Learning (RL) agents, especially when many of the actions are redundant or irrelevant. In such cases, it is sometimes easier to learn which actions not to take. In this work, we propose the Action-Elimination Deep Q-Network (AE-DQN) architecture that combines a Deep RL algorithm with an Action Elimination Network (AEN) that eliminates sub-optimal actions. The AEN is trained to predict invalid actions, supervised by an external elimination signal provided by the environment. Simulations demonstrate a considerable speedup and added robustness over vanilla DQN in text-based games with over a thousand discrete actions.
Deep learning is driving a radical paradigm shift in wireless communications, all the way from the application layer down to the physical layer. Despite this, there is an ongoing debate as to what additional values artificial intelligence (or machine learning) could bring to us, particularly on the physical layer design; and what penalties there may have? These questions motivate a fundamental rethinking of the wireless modem design in the artificial intelligence era. Through several physical-layer case studies, we argue for a significant role that machine learning could play, for instance in parallel error-control coding and decoding, channel equalization, interference cancellation, as well as multiuser and multiantenna detection. In addition, we will also discuss the fundamental bottlenecks of machine learning as well as their potential solutions in this paper.
Fluorescence microscopy images play the critical role of capturing spatial or spatiotemporal information of biomedical processes in life sciences. Their simple structures and semantics provide unique advantages in elucidating learning behavior of deep neural networks (DNNs). It is generally assumed that accurate image annotation is required to train DNNs for accurate image segmentation. In this study, however, we find that DNNs trained by label images in which nearly half (49%) of the binary pixel labels are randomly flipped provide largely the same segmentation performance. This suggests that DNNs learn high-level structures rather than pixel-level labels per se to segment fluorescence microscopy images. We refer to these structures as meta-structures. In support of the existence of the meta-structures, when DNNs are trained by a series of label images with progressively less meta-structure information, we find progressive degradation in their segmentation performance. Motivated by the learning behavior of DNNs trained by random labels and the characteristics of meta-structures, we propose an unsupervised segmentation model. Experiments show that it achieves remarkably competitive performance in comparison to supervised segmentation models.
Todays deep learning models are primarily trained on CPUs and GPUs. Although these models tend to have low error, they consume high power and utilize large amount of memory owing to double precision floating point learning parameters. Beyond the Moores law, a significant portion of deep learning tasks would run on edge computing systems, which will form an indispensable part of the entire computation fabric. Subsequently, training deep learning models for such systems will have to be tailored and adopted to generate models that have the following desirable characteristics: low error, low memory, and low power. We believe that deep neural networks (DNNs), where learning parameters are constrained to have a set of finite discrete values, running on neuromorphic computing systems would be instrumental for intelligent edge computing systems having these desirable characteristics. To this extent, we propose the Combinatorial Neural Network Training Algorithm (CoNNTrA), that leverages a coordinate gradient descent-based approach for training deep learning models with finite discrete learning parameters. Next, we elaborate on the theoretical underpinnings and evaluate the computational complexity of CoNNTrA. As a proof of concept, we use CoNNTrA to train deep learning models with ternary learning parameters on the MNIST, Iris and ImageNet data sets and compare their performance to the same models trained using Backpropagation. We use following performance metrics for the comparison: (i) Training error; (ii) Validation error; (iii) Memory usage; and (iv) Training time. Our results indicate that CoNNTrA models use 32x less memory and have errors at par with the Backpropagation models.
Machine learning based methods achieves impressive results in object classification and detection. Utilizing representative data of the visual world during the training phase is crucial to achieve good performance with such data driven approaches. However, it not always possible to access bias-free datasets thus, robustness to biased data is a desirable property for a learning system. Capsule Networks have been introduced recently and their tolerance to biased data has received little attention. This paper aims to fill this gap and proposes two experimental scenarios to assess the tolerance to imbalanced training data and to determine the generalization performance of a model with unfamiliar affine transformations of the images. This paper assesses dynamic routing and EM routing based Capsule Networks and proposes a comparison with Convolutional Neural Networks in the two tested scenarios. The presented results provide new insights into the behaviour of capsule networks.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
