Effective transfer learning of affordances for household robots

2014 ◽  
Author(s):  
Chang Wang ◽  
Koen V. Hindriks ◽  
Robert Babuska
Keyword(s):  
Transfer Learning ◽  
Effective Transfer

Effective Transfer Learning Algorithm in Spiking Neural Networks

2021 ◽  
pp. 1-13
Author(s):  
Qiugang Zhan ◽  
Guisong Liu ◽  
Xiurui Xie ◽  
Guolin Sun ◽  
Huajin Tang
Keyword(s):  
Neural Networks ◽  
Transfer Learning ◽  
Learning Algorithm ◽  
Spiking Neural Networks ◽  
Effective Transfer

scholarly journals Inductive Transfer Learning for Molecular Activity Prediction: Next-Gen QSAR Models with MolPMoFiT

2020 ◽  
Author(s):  
Xinhao Li ◽  
Denis Fourches
Keyword(s):  
Transfer Learning ◽  
High Throughput Screening ◽  
Structure Prediction ◽  
Large Scale ◽  
High Reliability ◽  
Structural Features ◽  
Fine Tuning ◽  
Qsar Modeling ◽  
Chemical Structures ◽  
Effective Transfer

<p>Deep neural networks can directly learn from chemical structures without extensive, user-driven selection of descriptors in order to predict molecular properties/activities with high reliability. But these approaches typically require large training sets to learn the endpoint-specific structural features and ensure reasonable prediction accuracy. Even though large datasets are becoming the new normal in drug discovery, especially when it comes to high-throughput screening or metabolomics datasets, one should also consider smaller datasets with challenging endpoints to model and forecast. Thus, it would be highly relevant to better utilize the tremendous compendium of unlabeled compounds from publicly-available datasets for improving the model performances for the user’s particular series of compounds. In this study, we propose the <b>Mol</b>ecular <b>P</b>rediction <b>Mo</b>del <b>Fi</b>ne-<b>T</b>uning (<b>MolPMoFiT</b>) approach, an effective transfer learning method based on self-supervised pre-training + task-specific fine-tuning for QSPR/QSAR modeling. A large-scale molecular structure prediction model is pre-trained using one million unlabeled molecules from ChEMBL in a self-supervised learning manner, and can then be fine-tuned on various QSPR/QSAR tasks for smaller chemical datasets with specific endpoints. Herein, the method is evaluated on four benchmark datasets (lipophilicity, FreeSolv, HIV, and blood-brain barrier penetration). The results showed the method can achieve strong performances for all four datasets compared to other state-of-the-art machine learning modeling techniques reported in the literature so far. <br></p>

scholarly journals Cross-Lingual Pre-Training Based Transfer for Zero-Shot Neural Machine Translation

2020 ◽  
Vol 34 (01) ◽  
pp. 115-122 ◽  
Author(s):  
Baijun Ji ◽  
Zhirui Zhang ◽  
Xiangyu Duan ◽  
Min Zhang ◽  
Boxing Chen ◽  
...  
Keyword(s):  
Machine Translation ◽  
Transfer Learning ◽  
Large Scale ◽  
Feature Space ◽  
Target Language ◽  
Smooth Transition ◽  
Training Methods ◽  
Neural Machine Translation ◽  
Cross Lingual ◽  
Effective Transfer

Transfer learning between different language pairs has shown its effectiveness for Neural Machine Translation (NMT) in low-resource scenario. However, existing transfer methods involving a common target language are far from success in the extreme scenario of zero-shot translation, due to the language space mismatch problem between transferor (the parent model) and transferee (the child model) on the source side. To address this challenge, we propose an effective transfer learning approach based on cross-lingual pre-training. Our key idea is to make all source languages share the same feature space and thus enable a smooth transition for zero-shot translation. To this end, we introduce one monolingual pre-training method and two bilingual pre-training methods to obtain a universal encoder for different languages. Once the universal encoder is constructed, the parent model built on such encoder is trained with large-scale annotated data and then directly applied in zero-shot translation scenario. Experiments on two public datasets show that our approach significantly outperforms strong pivot-based baseline and various multilingual NMT approaches.

scholarly journals A novel augmented deep transfer learning for classification of COVID-19 and other thoracic diseases from X-rays

2021 ◽  
Author(s):  
Fouzia Altaf ◽  
Syed M. S. Islam ◽  
Naeem Khalid Janjua
Keyword(s):  
Deep Learning ◽  
Medical Imaging ◽  
Transfer Learning ◽  
Medical Images ◽  
Training Data ◽  
Target Domain ◽  
Data Set ◽  
Learning Technique ◽  
Multi Class Classification ◽  
Effective Transfer

AbstractDeep learning has provided numerous breakthroughs in natural imaging tasks. However, its successful application to medical images is severely handicapped with the limited amount of annotated training data. Transfer learning is commonly adopted for the medical imaging tasks. However, a large covariant shift between the source domain of natural images and target domain of medical images results in poor transfer learning. Moreover, scarcity of annotated data for the medical imaging tasks causes further problems for effective transfer learning. To address these problems, we develop an augmented ensemble transfer learning technique that leads to significant performance gain over the conventional transfer learning. Our technique uses an ensemble of deep learning models, where the architecture of each network is modified with extra layers to account for dimensionality change between the images of source and target data domains. Moreover, the model is hierarchically tuned to the target domain with augmented training data. Along with the network ensemble, we also utilize an ensemble of dictionaries that are based on features extracted from the augmented models. The dictionary ensemble provides an additional performance boost to our method. We first establish the effectiveness of our technique with the challenging ChestXray-14 radiography data set. Our experimental results show more than 50% reduction in the error rate with our method as compared to the baseline transfer learning technique. We then apply our technique to a recent COVID-19 data set for binary and multi-class classification tasks. Our technique achieves 99.49% accuracy for the binary classification, and 99.24% for multi-class classification.

scholarly journals Inductive Transfer Learning for Molecular Activity Prediction: Next-Gen QSAR Models with MolPMoFiT

2019 ◽  
Author(s):  
Xinhao Li ◽  
Denis Fourches
Keyword(s):  
Transfer Learning ◽  
High Throughput Screening ◽  
Structure Prediction ◽  
Large Scale ◽  
High Reliability ◽  
Structural Features ◽  
Chemical Structures ◽  
Qsar Models ◽  
Benchmark Datasets ◽  
Effective Transfer

<p>Deep neural networks can directly learn from chemical structures without extensive, user-driven selection of descriptors in order to predict molecular properties/activities with high reliability. But these approaches typically require very large training sets to truly learn the best endpoint-specific structural features and ensure reasonable prediction accuracy. Even though large datasets are becoming the new normal in drug discovery, especially when it comes to high-throughput screening or metabolomics datasets, one should also consider smaller datasets with very challenging endpoints to model and forecast. Thus, it would be highly relevant to better utilize the tremendous compendium of unlabeled compounds from publicly-available datasets for improving the model performances for the user’s particular series of compounds. In this study, we propose the <b>M</b><b>ol</b>ecular <b>P</b>rediction <b>M</b><b>o</b>del <b>Fi</b>ne-<b>T</b>uning (<b>MolPMoFiT</b>) approach, an effective transfer learning method that can be applied to any QSPR/QSAR problems. A large-scale molecular structure prediction model is pre-trained using one million unlabeled molecules from ChEMBL in a self-supervised learning manor, and can then be fine-tuned on various QSPR/QSAR tasks for smaller chemical datasets with a specific endpoints. Herein, the method is evaluated on three benchmark datasets (lipophilicity, HIV, and blood-brain barrier penetration). The results showed the method can achieve comparable or better prediction performances on all three datasets compared to <i>state-of-the-art</i> prediction techniques reported in the literature so far. </p>

Diagnosis of interior damage with a convolutional neural network using simulation and measurement data

2021 ◽  
pp. 147592172110565
Author(s):  
Yanqing Bao ◽  
Sankaran Mahadevan
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Convolutional Neural Network ◽  
Transfer Learning ◽  
Computer Simulations ◽  
Training Data ◽  
Internal Damage ◽  
Damage Diagnosis ◽  
Effective Transfer ◽  
Traditional Image

Current deep learning applications in structural health monitoring (SHM) are mostly related to surface damage such as cracks and rust. Methods using traditional image processing techniques (such as filtering and edge detection) usually face difficulties in diagnosing internal damage in thicker specimens of heterogeneous materials. In this paper, we propose a damage diagnosis framework using a deep convolutional neural network (CNN) and transfer learning, focusing on internal damage such as voids and cracks. We use thermography to study the heat transfer characteristics and infer the presence of damage in the structure. It is challenging to obtain sufficient data samples for training deep neural networks, especially in the field of SHM. Therefore we use finite element (FE) computer simulations to generate a large volume of training data for the deep neural network, considering multiple damage shapes and locations. These computer-simulated data are used along with pre-trained convolutional cores of a sophisticated computer vision-based deep convolutional network to facilitate effective transfer learning. The CNN automatically generates features for damage diagnosis as opposed to manual feature generation in traditional image processing. Systematic parameter selection study is carried out to investigate accuracy versus computational expense in generating the training data. The methodology is demonstrated with an example of damage diagnosis in concrete, a heterogeneous material, using both computer simulations and laboratory experiments. The combination of FE simulation, transfer learning and experimental data is found to achieve high accuracy in damage localization with affordable effort.

Effective Transfer Learning for Identifying Similar Questions

2020 ◽  
Author(s):  
Clara H. McCreery ◽  
Namit Katariya ◽  
Anitha Kannan ◽  
Manish Chablani ◽  
Xavier Amatriain
Keyword(s):  
Transfer Learning ◽  
Effective Transfer

scholarly journals Inductive Transfer Learning for Molecular Activity Prediction: Next-Gen QSAR Models with MolPMoFiT

2020 ◽  
Author(s):  
Xinhao Li ◽  
Denis Fourches
Keyword(s):  
Transfer Learning ◽  
High Throughput Screening ◽  
Structure Prediction ◽  
Large Scale ◽  
High Reliability ◽  
Structural Features ◽  
Fine Tuning ◽  
Qsar Modeling ◽  
Chemical Structures ◽  
Effective Transfer

<p>Deep neural networks can directly learn from chemical structures without extensive, user-driven selection of descriptors in order to predict molecular properties/activities with high reliability. But these approaches typically require large training sets to learn the endpoint-specific structural features and ensure reasonable prediction accuracy. Even though large datasets are becoming the new normal in drug discovery, especially when it comes to high-throughput screening or metabolomics datasets, one should also consider smaller datasets with challenging endpoints to model and forecast. Thus, it would be highly relevant to better utilize the tremendous compendium of unlabeled compounds from publicly-available datasets for improving the model performances for the user’s particular series of compounds. In this study, we propose the <b>Mol</b>ecular <b>P</b>rediction <b>Mo</b>del <b>Fi</b>ne-<b>T</b>uning (<b>MolPMoFiT</b>) approach, an effective transfer learning method based on self-supervised pre-training + task-specific fine-tuning for QSPR/QSAR modeling. A large-scale molecular structure prediction model is pre-trained using one million unlabeled molecules from ChEMBL in a self-supervised learning manner, and can then be fine-tuned on various QSPR/QSAR tasks for smaller chemical datasets with specific endpoints. Herein, the method is evaluated on four benchmark datasets (lipophilicity, FreeSolv, HIV, and blood-brain barrier penetration). The results showed the method can achieve strong performances for all four datasets compared to other state-of-the-art machine learning modeling techniques reported in the literature so far. <br></p>

Merging with Extraction Method for Transfer Learning in Actor-Critic

2011 ◽  
Vol 15 (7) ◽  
pp. 814-821
Author(s):  
Toshiaki Takano ◽  
◽  
Haruhiko Takase ◽  
Hiroharu Kawanaka ◽  
Shinji Tsuruoka ◽  
...  
Keyword(s):  
Transfer Learning ◽  
Weighted Average ◽  
Previous Method ◽  
Training Phase ◽  
Trial And Error ◽  
Training Algorithm ◽  
Target Task ◽  
Transfer Method ◽  
Effective Transfer ◽  
Selection Phase

This paper aims to accelerate learning process of actor-critic method, which is one of the major reinforcement learning algorithms, by a transfer learning. Transfer learning accelerates learning processes for the target task by reusing knowledge of source policies for each source task. In general, it consists of a selection phase and a training phase. Agents select source policies that are similar to the target one without trial and error, and train the target task by referring selected policies. In this paper, we discuss the training phase, and the rest of the training algorithm is based on our previous method. We proposed the effective transfer method that consists of the extractionmethod and the mergingmethod. Agents extract action preferences that are related to reliable states, and state values that lead to preferred states. Extracted parameters are merged into the current parameters by taking weighted average. We apply the proposed algorithm to simple maze tasks, and show the effectiveness of the proposed method: reduce 16% episodes and 55% failures without transfer.

Sign in / Sign up

Export Citation Format

Share Document