Improved Multitask Learning in Neural Networks for Predicting Selective Compounds

The classification of the text involving the process of identification and categorization of text is a tedious and a challenging task too. The Capsules Network (Caps-Net) which is a unique architecture with the capability to confiscate the basic attributes comprising the insights of the particular field that could help in bridging the knowledge gap existing between the source and the destination tasks and capability learn more robust representation than the CNN-Convolutional neural networks in the image classification domain is utilized in the paper to classify the text. As the multi –task learning capability enables to part insights between the tasks that are related and enhances data used in training indirectly, the Caps-Net based multi task learning frame work is proposed in the paper. The proposed architecture including the Caps-Net effectively classifies the text and minimizes the interference experienced among the multiple tasks in the multi –task learning. The architecture put forward is evaluated using various text classification dataset ensuring the efficacy of the proffered frame work

Download Full-text

Creating, Managing, and Understanding Large, Sparse, Multitask Neural Networks

10.31219/osf.io/bv4qp ◽

2020 ◽

Author(s):

Harshvardhan Sikka

Keyword(s):

Neural Network ◽

Neural Networks ◽

Deep Learning ◽

Text Classification ◽

Multitask Learning ◽

Learning Tasks ◽

Deep Networks ◽

Classification Tasks

One of the popular directions in Deep Learning (DL) research has been to build larger and more complex deep networks that can perform well on several different learning tasks, commonly known as multitask learning. This work is usually done within specific domains, e.g. multitask models that perform captioning, translation, and text classification tasks. Some work has been done in building multimodal/crossmodal networks that use deep networks with a combination of different neural network primitives (Convolutional Layers, Recurrent Layers, Mixture of Expert layers, etc). This paper explores various topics and ideas that may prove relevant to large, sparse, multitask networks and explores the potential for a general approach to building and managing these networks. A framework to automatically build, update, and interpret modular LSMNs is presented in the context of current tooling and theory.

Download Full-text

HalluciNet-ing Spatiotemporal Representations Using a 2D-CNN

Signals ◽

10.3390/signals2030037 ◽

2021 ◽

Vol 2 (3) ◽

pp. 604-618

Author(s):

Paritosh Parmar ◽

Brendan Morris

Keyword(s):

Neural Networks ◽

State Of The Art ◽

Scene Recognition ◽

Multitask Learning ◽

Training Phase ◽

Dynamic Scene ◽

Improve Performance ◽

Computing Power ◽

Practical Standpoint ◽

3D Cnn

Spatiotemporal representations learned using 3D convolutional neural networks (CNN) are currently used in state-of-the-art approaches for action-related tasks. However, 3D-CNN are notorious for being memory and compute resource intensive as compared with more simple 2D-CNN architectures. We propose to hallucinate spatiotemporal representations from a 3D-CNN teacher with a 2D-CNN student. By requiring the 2D-CNN to predict the future and intuit upcoming activity, it is encouraged to gain a deeper understanding of actions and how they evolve. The hallucination task is treated as an auxiliary task, which can be used with any other action-related task in a multitask learning setting. Thorough experimental evaluation, it is shown that the hallucination task indeed helps improve performance on action recognition, action quality assessment, and dynamic scene recognition tasks. From a practical standpoint, being able to hallucinate spatiotemporal representations without an actual 3D-CNN can enable deployment in resource-constrained scenarios, such as with limited computing power and/or lower bandwidth. We also observed that our hallucination task has utility not only during the training phase, but also during the pre-training phase.

Download Full-text

Identification of Social-Media Platform of Videos through the Use of Shared Features

Journal of Imaging ◽

10.3390/jimaging7080140 ◽

2021 ◽

Vol 7 (8) ◽

pp. 140

Author(s):

Luca Maiano ◽

Irene Amerini ◽

Lorenzo Ricciardi Celsi ◽

Aris Anagnostopoulos

Keyword(s):

Neural Networks ◽

Social Networks ◽

Social Media ◽

Transfer Learning ◽

Multitask Learning ◽

Social Media Platform ◽

New Methods ◽

Media Platform ◽

Revenge Porn ◽

Illegal Activities

Videos have become a powerful tool for spreading illegal content such as military propaganda, revenge porn, or bullying through social networks. To counter these illegal activities, it has become essential to try new methods to verify the origin of videos from these platforms. However, collecting datasets large enough to train neural networks for this task has become difficult because of the privacy regulations that have been enacted in recent years. To mitigate this limitation, in this work we propose two different solutions based on transfer learning and multitask learning to determine whether a video has been uploaded from or downloaded to a specific social platform through the use of shared features with images trained on the same task. By transferring features from the shallowest to the deepest levels of the network from the image task to videos, we measure the amount of information shared between these two tasks. Then, we introduce a model based on multitask learning, which learns from both tasks simultaneously. The promising experimental results show, in particular, the effectiveness of the multitask approach. According to our knowledge, this is the first work that addresses the problem of social media platform identification of videos through the use of shared features.

Download Full-text