Radar Echo Spatiotemporal Sequence Prediction Using an Improved ConvGRU Deep Learning Model

Precipitation nowcasting is extremely important in disaster prevention and mitigation, and can improve the quality of meteorological forecasts. In recent years, deep learning-based spatiotemporal sequence prediction models have been widely used in precipitation nowcasting, obtaining better prediction results than numerical weather prediction models and traditional radar echo extrapolation results. Because existing deep learning models rarely consider the inherent interactions between the model input data and the previous output, model prediction results do not sufficiently meet the actual forecast requirement. We propose a Modified Convolutional Gated Recurrent Unit (M-ConvGRU) model that performs convolution operations on the input data and previous output of a GRU network. Moreover, this adopts an encoder–forecaster structure to better capture the characteristics of spatiotemporal correlation in radar echo maps. The results of multiple experiments demonstrate the effectiveness of the proposed model. The balanced mean absolute error (B-MAE) and balanced mean squared error (B-MSE) of M-ConvGRU are slightly lower than Convolutional Long Short-Term Memory (ConvLSTM), but the mean absolute error (MAE) and mean squared error (MSE) of M-ConvGRU are 6.29% and 10.25% lower than ConvLSTM, and the prediction accuracy and prediction performance for strong echo regions were also improved.

Gated recurrence enables simple and accurate sequence prediction in stochastic, changing, and structured environments

From decision making to perception to language, predicting what is coming next is crucial. It is also challenging in stochastic, changing, and structured environments; yet the brain makes accurate predictions in many situations. What computational architecture could enable this feat? Bayesian inference makes optimal predictions but is prohibitively difficult to compute. Here, we show that a specific recurrent neural network architecture enables simple and accurate solutions in several environments. This architecture relies on three mechanisms: gating, lateral connections, and recurrent weight training. Like the optimal solution and the human brain, such networks develop internal representations of their changing environment (including estimates of the environment's latent variables and the precision of these estimates), leverage multiple levels of latent structure, and adapt their effective learning rate to changes without changing their connection weights. Being ubiquitous in the brain, gated recurrence could therefore serve as a generic building block to predict in real-life environments.

A Method for Computationally Constructing Eukaryotic Synthetic Signal Peptide Sequences

We developed a computational method for constructing synthetic signal peptides from a base set of signal peptides (SPs) and non-SP sequences. A large number of structured "building blocks", represented as m-step ordered pairs of amino acids, are extracted from the base. Using a straightforward procedure, the building blocks enable the construction of a diverse set of synthetic SPs that could be utilized for industrial and therapeutic purposes. We have validated the proposed methodology using existing sequence prediction platforms such as Signal-BLAST and MULocDeep. In one experiment, 9,555 protein sequences were generated from a large randomly selected set of "building blocks". Signal-BLAST identified 8,444 (88%) of the sequences as signal peptides. In addition, the Signal-BLAST tool predicted that the generated synthetic sequences belonged to 854 distinct eukaryotic organisms. Here, we provide detailed descriptions and results from various experiments illustrating the potential usefulness of the methodology in generating signal peptide protein sequences.

Learning Intuitive Physics and One-Shot Imitation Using State-Action-Prediction Self-Organizing Maps

Human learning and intelligence work differently from the supervised pattern recognition approach adopted in most deep learning architectures. Humans seem to learn rich representations by exploration and imitation, build causal models of the world, and use both to flexibly solve new tasks. We suggest a simple but effective unsupervised model which develops such characteristics. The agent learns to represent the dynamical physical properties of its environment by intrinsically motivated exploration and performs inference on this representation to reach goals. For this, a set of self-organizing maps which represent state-action pairs is combined with a causal model for sequence prediction. The proposed system is evaluated in the cartpole environment. After an initial phase of playful exploration, the agent can execute kinematic simulations of the environment’s future and use those for action planning. We demonstrate its performance on a set of several related, but different one-shot imitation tasks, which the agent flexibly solves in an active inference style.

ProDCoNN-server: a web server for protein sequence prediction and design from a three-dimensional structure

We present ProDCoNN-server, a web server for protein sequence design and prediction from a given protein structure. The server is based on a previously developed deep learning model for protein design, ProDCoNN, which achieved state-of-the-art performance when tested on large numbers of test proteins and benchmark datasets. The prediction is very fast compared with other protein sequence prediction servers - it takes only a few minutes for a query protein on average. Two models could be selected for different purposes: BBO for full sequence prediction, extendable for multiple sequence generation, and BBS for single position prediction with the type of other residues known. ProDCoNN-server outputs the predicted sequence and the probability matrix for each amino acid at each predicted residue. The probability matrix can also be visualized as a sequence logos figure (BBO) or probability distribution plot (BBS). The server is available at: https://prodconn.stat.fsu.edu/.

Dancing with the sound in edge computing environments

Conventional motion predictions have achieved promising performance. However, the length of the predicted motion sequences of most literatures are short, and the rhythm of the generated pose sequence has rarely been explored. To pursue high quality, rhythmic, and long-term pose sequence prediction, this paper explores a novel dancing with the sound task, which is appealing and challenging in computer vision field. To tackle this problem, a novel model is proposed, which takes the sound as an indicator input and outputs the dancing pose sequence. Specifically, our model is based on the variational autoencoder (VAE) framework, which encodes the continuity and rhythm of the sound information into the hidden space to generate a coherent, diverse, rhythmic and long-term pose video. Extensive experiments validated the effectiveness of audio cues in the generation of dancing pose sequences. Concurrently, a novel dataset of audiovisual multimodal sequence generation has been released to promote the development of this field.

Fully Homomorphically Encrypted Deep Learning as a Service

Fully Homomorphic Encryption (FHE) is a relatively recent advancement in the field of privacy-preserving technologies. FHE allows for the arbitrary depth computation of both addition and multiplication, and thus the application of abelian/polynomial equations, like those found in deep learning algorithms. This project investigates how FHE with deep learning can be used at scale toward accurate sequence prediction, with a relatively low time complexity, the problems that such a system incurs, and mitigations/solutions for such problems. In addition, we discuss how this could have an impact on the future of data privacy and how it can enable data sharing across various actors in the agri-food supply chain, hence allowing the development of machine learning-based systems. Finally, we find that although FHE incurs a high spatial complexity cost, the run time is within expected reasonable bounds, while allowing for absolutely private predictions to be made, in our case for milk yield prediction with a Mean Absolute Percentage Error (MAPE) of 12.4% and an accuracy of 87.6% on average.