scholarly journals Cross-situational word learning with multimodal neural networks

2021 ◽  
Author(s):  
Wai Keen Vong ◽  
Brenden M. Lake
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Word Learning ◽  
Network Architecture ◽  
Question Answering ◽  
Cognitive Models ◽  
Learning Approaches ◽  
Neural Network Learning ◽  
Single Epoch

In order to learn the mappings from words to referents, children must integrate co-occurrence information across individually ambiguous pairs of scenes and utterances, a challenge known as cross-situational word learning. In machine learning, recent multimodal neural networks have been shown to learn meaningful visual-linguistic mappings from cross-situational data, as needed to solve problems such as image captioning and visual question answering. These networks are potentially appealing as cognitive models because they can learn from raw visual and linguistic stimuli, something previous cognitive models have not addressed. In this paper, we examine whether recent machine learning approaches can help explain various behavioral phenomena from the psychological literature on cross-situational word learning. We consider two variants of a multimodal neural network architecture, and look at seven different phenomena associated with cross-situational word learning, and word learning more generally. Our results show that these networks can learn word-referent mappings from a single epoch of training, matching the amount of training found in cross-situational word learning experiments. Additionally, these networks capture some, but not all of the phenomena we studied, with all of the failures related to reasoning via mutual exclusivity. These results provide insight into the kinds of phenomena that arise naturally from relatively generic neural network learning algorithms, and which word learning phenomena require additional inductive biases.

scholarly journals Harnessing Deep Neural Networks to Solve Inverse Problems in Quantum Dynamics: Machine-Learned Predictions of Time-Dependent Optimal Control Fields

2020 ◽  
Author(s):  
Xian Wang ◽  
Anshuman Kumar ◽  
Christian Shelton ◽  
Bryan Wong
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Optimal Control ◽  
Quantum Dynamics ◽  
Deep Neural Networks ◽  
Time Dependent ◽  
Learning Approaches ◽  
Quantum Dynamical ◽  
Quantum Dynamical Systems

Inverse problems continue to garner immense interest in the physical sciences, particularly in the context of controlling desired phenomena in non-equilibrium systems. In this work, we utilize a series of deep neural networks for predicting time-dependent optimal control fields, <i>E(t)</i>, that enable desired electronic transitions in reduced-dimensional quantum dynamical systems. To solve this inverse problem, we investigated two independent machine learning approaches: (1) a feedforward neural network for predicting the frequency and amplitude content of the power spectrum in the frequency domain (i.e., the Fourier transform of <i>E(t)</i>), and (2) a cross-correlation neural network approach for directly predicting <i>E(t)</i> in the time domain. Both of these machine learning methods give complementary approaches for probing the underlying quantum dynamics and also exhibit impressive performance in accurately predicting both the frequency and strength of the optimal control field. We provide detailed architectures and hyperparameters for these deep neural networks as well as performance metrics for each of our machine-learned models. From these results, we show that machine learning approaches, particularly deep neural networks, can be employed as a cost-effective statistical approach for designing electromagnetic fields to enable desired transitions in these quantum dynamical systems.

scholarly journals PARROT is a flexible recurrent neural network framework for analysis of large protein datasets

eLife ◽  
2021 ◽  
Vol 10 ◽  
Author(s):  
Daniel Griffith ◽  
Alex S Holehouse
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
High Throughput ◽  
Recurrent Neural Network ◽  
Transcriptional Activation ◽  
Network Architecture ◽  
Learning Approaches ◽  
Large Protein ◽  
Protein Datasets

The rise of high-throughput experiments has transformed how scientists approach biological questions. The ubiquity of large-scale assays that can test thousands of samples in a day has necessitated the development of new computational approaches to interpret this data. Among these tools, machine learning approaches are increasingly being utilized due to their ability to infer complex nonlinear patterns from high-dimensional data. Despite their effectiveness, machine learning (and in particular deep learning) approaches are not always accessible or easy to implement for those with limited computational expertise. Here we present PARROT, a general framework for training and applying deep learning-based predictors on large protein datasets. Using an internal recurrent neural network architecture, PARROT is capable of tackling both classification and regression tasks while only requiring raw protein sequences as input. We showcase the potential uses of PARROT on three diverse machine learning tasks: predicting phosphorylation sites, predicting transcriptional activation function of peptides generated by high-throughput reporter assays, and predicting the fibrillization propensity of amyloid beta with data generated by deep mutational scanning. Through these examples, we demonstrate that PARROT is easy to use, performs comparably to state-of-the-art computational tools, and is applicable for a wide array of biological problems.

scholarly journals ThriftyNets: Convolutional Neural Networks with Tiny Parameter Budget

IoT ◽  
2021 ◽  
Vol 2 (2) ◽  
pp. 222-235
Author(s):  
Guillaume Coiffier ◽  
Ghouthi Boukli Hacene ◽  
Vincent Gripon
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Convolutional Neural Network ◽  
Spatial Resolution ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
State Of The Art ◽  
Feature Maps ◽  
Neural Network Architecture

Deep Neural Networks are state-of-the-art in a large number of challenges in machine learning. However, to reach the best performance they require a huge pool of parameters. Indeed, typical deep convolutional architectures present an increasing number of feature maps as we go deeper in the network, whereas spatial resolution of inputs is decreased through downsampling operations. This means that most of the parameters lay in the final layers, while a large portion of the computations are performed by a small fraction of the total parameters in the first layers. In an effort to use every parameter of a network at its maximum, we propose a new convolutional neural network architecture, called ThriftyNet. In ThriftyNet, only one convolutional layer is defined and used recursively, leading to a maximal parameter factorization. In complement, normalization, non-linearities, downsamplings and shortcut ensure sufficient expressivity of the model. ThriftyNet achieves competitive performance on a tiny parameters budget, exceeding 91% accuracy on CIFAR-10 with less than 40 k parameters in total, 74.3% on CIFAR-100 with less than 600 k parameters, and 67.1% On ImageNet ILSVRC 2012 with no more than 4.15 M parameters. However, the proposed method typically requires more computations than existing counterparts.

scholarly journals Harnessing Deep Neural Networks to Solve Inverse Problems in Quantum Dynamics: Machine-Learned Predictions of Time-Dependent Optimal Control Fields

2020 ◽  
Author(s):  
Xian Wang ◽  
Anshuman Kumar ◽  
Christian Shelton ◽  
Bryan Wong
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Optimal Control ◽  
Quantum Dynamics ◽  
Deep Neural Networks ◽  
Time Dependent ◽  
Learning Approaches ◽  
Quantum Dynamical ◽  
Quantum Dynamical Systems

Inverse problems continue to garner immense interest in the physical sciences, particularly in the context of controlling desired phenomena in non-equilibrium systems. In this work, we utilize a series of deep neural networks for predicting time-dependent optimal control fields, <i>E(t)</i>, that enable desired electronic transitions in reduced-dimensional quantum dynamical systems. To solve this inverse problem, we investigated two independent machine learning approaches: (1) a feedforward neural network for predicting the frequency and amplitude content of the power spectrum in the frequency domain (i.e., the Fourier transform of <i>E(t)</i>), and (2) a cross-correlation neural network approach for directly predicting <i>E(t)</i> in the time domain. Both of these machine learning methods give complementary approaches for probing the underlying quantum dynamics and also exhibit impressive performance in accurately predicting both the frequency and strength of the optimal control field. We provide detailed architectures and hyperparameters for these deep neural networks as well as performance metrics for each of our machine-learned models. From these results, we show that machine learning approaches, particularly deep neural networks, can be employed as a cost-effective statistical approach for designing electromagnetic fields to enable desired transitions in these quantum dynamical systems.

scholarly journals Conquering the CNN Over-Parameterization Dilemma: A Volterra Filtering Approach for Action Recognition

2020 ◽  
Vol 34 (07) ◽  
pp. 11948-11956
Author(s):  
Siddharth Roheda ◽  
Hamid Krim
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Action Recognition ◽  
Network Architecture ◽  
Video Sequence ◽  
Spatial Information ◽  
State Of The Art ◽  
Parallel Implementation ◽  
Filtering Approach

The importance of inference in Machine Learning (ML) has led to an explosive number of different proposals in ML, and particularly in Deep Learning. In an attempt to reduce the complexity of Convolutional Neural Networks, we propose a Volterra filter-inspired Network architecture. This architecture introduces controlled non-linearities in the form of interactions between the delayed input samples of data. We propose a cascaded implementation of Volterra Filtering so as to significantly reduce the number of parameters required to carry out the same classification task as that of a conventional Neural Network. We demonstrate an efficient parallel implementation of this Volterra Neural Network (VNN), along with its remarkable performance while retaining a relatively simpler and potentially more tractable structure. Furthermore, we show a rather sophisticated adaptation of this network to nonlinearly fuse the RGB (spatial) information and the Optical Flow (temporal) information of a video sequence for action recognition. The proposed approach is evaluated on UCF-101 and HMDB-51 datasets for action recognition, and is shown to outperform state of the art CNN approaches.

scholarly journals Synthesis of Neural Network Architecture for Recognition of Sea-Going Ship Images

2020 ◽  
Vol 24 (1) ◽  
pp. 130-143
Author(s):  
D. I. Konarev ◽  
A. A. Gulamov
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Image Recognition ◽  
Network Architecture ◽  
Test Sample ◽  
Feature Maps ◽  
Noticeable Effect ◽  
Current Task ◽  
Correct Pattern

Purpose of research. The current task is to monitor ships using video surveillance cameras installed along the canal. It is important for information communication support for navigation of the Moscow Canal. The main subtask is direct recognition of ships in an image or video. Implementation of a neural network is perspectively.Methods. Various neural network are described. images of ships are an input data for the network. The learning sample uses CIFAR-10 dataset. The network is built and trained by using Keras and TensorFlow machine learning libraries.Results. Implementation of curving artificial neural networks for problems of image recognition is described. Advantages of such architecture when working with images are also described. The selection of Python language for neural network implementation is justified. The main used libraries of machine learning, such as TensorFlow and Keras are described. An experiment has been conducted to train swirl neural networks with different architectures based on Google collaboratoty service. The effectiveness of different architectures was evaluated as a percentage of correct pattern recognition in the test sample. Conclusions have been drawn about parameters influence of screwing neural network on showing its effectiveness.Conclusion. The network with a single curl layer in each cascade showed insufficient results, so three-stage curls with two and three curl layers in each cascade were used. Feature map extension has the greatest impact on the accuracy of image recognition. The increase in cascades' number has less noticeable effect and the increase in the number of screwdriver layers in each cascade does not always have an increase in the accuracy of the neural network. During the study, a three-frame network with two buckling layers in each cascade and 128 feature maps is defined as an optimal architecture of neural network under described conditions. operability checking of architecture's part under consideration on random images of ships confirmed the correctness of optimal architecture choosing.

scholarly journals Privacy-Preserving Federated Neural Network Learning for Disease-Associated Cell Classification

2022 ◽  
Author(s):  
Sinem Sav ◽  
Jean-Philippe Bossuat ◽  
Juan R. Troncoso-Pastoriza ◽  
Manfred Claassen ◽  
Jean-Pierre Hubaux
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Network Architecture ◽  
Homomorphic Encryption ◽  
Privacy Preserving ◽  
Model Parameters ◽  
Patient Privacy ◽  
Learning Models ◽  
Machine Learning Models

Training accurate and robust machine learning models requires a large amount of data that is usually scattered across data-silos. Sharing or centralizing the data of different healthcare institutions is, however, unfeasible or prohibitively difficult due to privacy regulations. In this work, we address this problem by using a novel privacy-preserving federated learning-based approach, PriCell, for complex machine learning models such as convolutional neural networks. PriCell relies on multiparty homomorphic encryption and enables the collaborative training of encrypted neural networks with multiple healthcare institutions. We preserve the confidentiality of each institutions' input data, of any intermediate values, and of the trained model parameters. We efficiently replicate the training of a published state-of-the-art convolutional neural network architecture in a decentralized and privacy-preserving manner. Our solution achieves an accuracy comparable to the one obtained with the centralized solution, with an improvement of at least one-order-of-magnitude in execution time with respect to prior secure solutions. Our work guarantees patient privacy and ensures data utility for efficient multi-center studies involving complex healthcare data.

scholarly journals PARROT: a flexible recurrent neural network framework for analysis of large protein datasets

2021 ◽  
Author(s):  
Daniel Griffith ◽  
Alex S Holehouse
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
High Throughput ◽  
Recurrent Neural Network ◽  
Transcriptional Activation ◽  
Network Architecture ◽  
Learning Approaches ◽  
Large Protein ◽  
Protein Datasets

The rise of high-throughput experiments has transformed how scientists approach biological questions. The ubiquity of large-scale assays that can test thousands of samples in a day has necessitated the development of new computational approaches to interpret this data. Among these tools, machine learning approaches are increasingly being utilized due to their ability to infer complex non-linear patterns from high-dimensional data. Despite their effectiveness, machine learning (and in particular deep learning) approaches are not always accessible or easy to implement for those with limited computational expertise. Here we present PARROT, a general framework for training and applying deep learning-based predictors on large protein datasets. Using an internal recurrent neural network architecture, PARROT is capable of tackling both classification and regression tasks while only requiring raw protein sequences as input. We showcase the potential uses of PARROT on three diverse machine learning tasks: predicting phosphorylation sites, predicting transcriptional activation function of peptides generated by high-throughput reporter assays, and predicting the fibrillization propensity of amyloid-beta with data generated by deep mutational scanning. Through these examples, we demonstrate that PARROT is easy to use, performs comparably to state-of-the-art computational tools, and is applicable for a wide array of biological problems.

RANDOM MULTI-MODAL DEEP LEARNING IN THE PROBLEM OF IMAGE RECOGNITION

2021 ◽  
pp. 21-26
Author(s):  
А.И. Паршин ◽  
М.Н. Аралов ◽  
В.Ф. Барабанов ◽  
Н.И. Гребенникова
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Image Recognition ◽  
Recurrent Neural Networks ◽  
Network Architecture ◽  
Deep Neural Networks ◽  
Machine Learning Algorithms ◽  
Complex Data ◽  
Advantages And Disadvantages

Задача распознавания изображений - одна из самых сложных в машинном обучении, требующая от исследователя как глубоких знаний, так и больших временных и вычислительных ресурсов. В случае использования нелинейных и сложных данных применяются различные архитектуры глубоких нейронных сетей, но при этом сложным вопросом остается проблема выбора нейронной сети. Основными архитектурами, используемыми повсеместно, являются свёрточные нейронные сети (CNN), рекуррентные нейронные сети (RNN), глубокие нейронные сети (DNN). На основе рекуррентных нейронных сетей (RNN) были разработаны сети с долгой краткосрочной памятью (LSTM) и сети с управляемыми реккурентными блоками (GRU). Каждая архитектура нейронной сети имеет свою структуру, свои настраиваемые и обучаемые параметры, обладает своими достоинствами и недостатками. Комбинируя различные виды нейронных сетей, можно существенно улучшить качество предсказания в различных задачах машинного обучения. Учитывая, что выбор оптимальной архитектуры сети и ее параметров является крайне трудной задачей, рассматривается один из методов построения архитектуры нейронных сетей на основе комбинации свёрточных, рекуррентных и глубоких нейронных сетей. Показано, что такие архитектуры превосходят классические алгоритмы машинного обучения The image recognition task is one of the most difficult in machine learning, requiring both deep knowledge and large time and computational resources from the researcher. In the case of using nonlinear and complex data, various architectures of deep neural networks are used but the problem of choosing a neural network remains a difficult issue. The main architectures used everywhere are convolutional neural networks (CNN), recurrent neural networks (RNN), deep neural networks (DNN). Based on recurrent neural networks (RNNs), Long Short Term Memory Networks (LSTMs) and Controlled Recurrent Unit Networks (GRUs) were developed. Each neural network architecture has its own structure, customizable and trainable parameters, and advantages and disadvantages. By combining different types of neural networks, you can significantly improve the quality of prediction in various machine learning problems. Considering that the choice of the optimal network architecture and its parameters is an extremely difficult task, one of the methods for constructing the architecture of neural networks based on a combination of convolutional, recurrent and deep neural networks is considered. We showed that such architectures are superior to classical machine learning algorithms

scholarly journals Fundamentals of Neural Networks

2021 ◽  
Vol 9 (VIII) ◽  
pp. 407-426
Author(s):  
Amey Thakur
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Neural Networks ◽  
Network Models ◽  
Learning Approaches ◽  
Neural Network Models ◽  
Comprehensive Review ◽  
Technological Advances ◽  
Neuro Fuzzy ◽  
Different Types

The purpose of this study is to familiarise the reader with the foundations of neural networks. Artificial Neural Networks (ANNs) are algorithm-based systems that are modelled after Biological Neural Networks (BNNs). Neural networks are an effort to use the human brain's information processing skills to address challenging real-world AI issues. The evolution of neural networks and their significance are briefly explored. ANNs and BNNs are contrasted, and their qualities, benefits, and disadvantages are discussed. The drawbacks of the perceptron model and their improvement by the sigmoid neuron and ReLU neuron are briefly discussed. In addition, we give a bird's-eye view of the different Neural Network models. We study neural networks (NNs) and highlight the different learning approaches and algorithms used in Machine Learning and Deep Learning. We also discuss different types of NNs and their applications. A brief introduction to Neuro-Fuzzy and its applications with a comprehensive review of NN technological advances is provided.

Sign in / Sign up

Export Citation Format

Share Document