Time-state neural networks (TSNN) for phoneme identification by considering temporal structure of phonemic features

To perform many critical manipulation tasks successfully, human-robot mimicking systems should not only accurately copy the position of a human hand, but its orientation as well. Deep learning methods trained from pairs of corresponding human and robot poses offer one promising approach for constructing a human-robot mapping to accomplish this. However, ignoring the spatial and temporal structure of this mapping makes learning it less effective. We propose two different hierarchical architectures that leverage the structural and temporal human-robot mapping. We partially separate the robotic manipulator's end-effector position and orientation while considering the mutual coupling effects between them. This divides the main problem---making the robot match the human's hand position and mimic its orientation accurately along an unknown trajectory---into several sub-problems. We address these using different recurrent neural networks (RNNs) with Long-Short Term Memory (LSTM) that we combine and train hierarchically based on the coupling over the aspects of the robot that each controls. We evaluate our proposed architectures using a virtual reality system to track human table tennis motions and compare with single artificial neural network (ANN) and RNN models. We compare the benefits of using deep learning neural networks with and without our architectures and find smaller errors in position and orientation, along with increased flexibility in wrist movement are obtained by our proposed architectures. Also, we propose a hybrid approach to collect the training dataset. The hybrid training dataset is collected by two approaches when the robot mimics human motions (standard learn from demonstrator LfD) and when the human mimics robot motions (LfDr). We evaluate the hybrid training dataset and show that the performance of the machine learning system trained by the hybrid training dataset is better with less error and faster training time compared to using the collected dataset using standard LfD approach.

Download Full-text

Flexibility in motor timing constrains the topology and dynamics of pattern generator circuits

10.1101/033472 ◽

2015 ◽

Cited By ~ 1

Author(s):

Cengiz Pehlevan ◽

Farhan Ali ◽

Bence P. Ölveczky

Keyword(s):

Neural Networks ◽

Motor Skills ◽

Temporal Structure ◽

Pattern Generator ◽

Network Activity ◽

Recurrent Networks ◽

Motor Timing ◽

Feedforward Networks ◽

Stereotyped Behaviors ◽

Precise Movement

SummaryTemporally precise movement patterns underlie many motor skills and innate actions, yet the flexibility with which the timing of such stereotyped behaviors can be modified is poorly understood. To probe this, we induced adaptive changes to the temporal structure of birdsong. We find that the duration of specific song segments can be modified without affecting the timing in other parts of the song. We derive formal prescriptions for how neural networks can implement such flexible motor timing. We find that randomly connected recurrent networks, a common approximation for how neocortex is wired, do not generally conform to these, though certain implementations can approximate them. We show that feedforward networks, by virtue of their one-to-one mapping between network activity and time, are better suited. Our study provides general prescriptions for pattern generator networks that implement flexible motor timing, an important aspect of many motor skills, including birdsong and human speech.

Download Full-text

Forecasting Financial Time Series through Causal and Dilated Convolutional Neural Networks

Entropy ◽

10.3390/e22101094 ◽

2020 ◽

Vol 22 (10) ◽

pp. 1094

Author(s):

Lukas Börjesson ◽

Martin Singull

Keyword(s):

Neural Networks ◽

Financial Time Series ◽

Temporal Structure ◽

Financial Data ◽

Stock Index ◽

Future Price ◽

Financial Time ◽

Speech Generation ◽

Closing Price ◽

Test Sets

In this paper, predictions of future price movements of a major American stock index were made by analyzing past movements of the same and other correlated indices. A model that has shown very good results in audio and speech generation was modified to suit the analysis of financial data and was then compared to a base model, restricted by assumptions made for an efficient market. The performance of any model, trained by looking at past observations, is heavily influenced by how the division of the data into train, validation and test sets is made. This is further exaggerated by the temporal structure of the financial data, which means that the causal relationship between the predictors and the response is dependent on time. The complexity of the financial system further increases the struggle to make accurate predictions, but the model suggested here was still able to outperform the naive base model by more than 20% and 37%, respectively, when predicting the next day’s closing price and the next day’s trend.

Download Full-text