Although Transformer-based methods have significantly improved state-of-the-art results for long-term series forecasting, they are not only computationally expensive but more importantly, are unable to capture the global view of time series (e.g. overall trend). To address these problems, we propose to combine Transformer with the seasonal-trend decomposition method, in which the decomposition method captures the global profile of time series while Transformers capture more detailed structures. To further enhance the performance of Transformer for long-term prediction, we exploit the fact that most time series tend to have a sparse representation in well-known basis such as Fourier transform, and develop a frequency enhanced Transformer. Besides being more effective, the proposed method, termed as Frequency Enhanced Decomposed Transformer ({\bf FEDformer}), is more efficient than standard Transformer with a linear complexity to the sequence length. Our empirical studies with six benchmark datasets show that compared with state-of-the-art methods, FEDformer can reduce prediction error by $14.8\%$ and $22.6\%$ for multivariate and univariate time series, respectively. the code will be released soon.

The South African patent office made history in July when it issued a patent that listed an artificial intelligence system as the inventor. The patent is for a food container that uses fractal designs to create pits and bulges in its sides. Designed for the packaging industry, the new configuration allows containers to fit more tightly together so they can be transported better. The shape also makes it easier for robotic arms to pick up the containers. The patent's owner, AI pioneer Stephen L. Thaler, created the inventor, the AI system known as Dabus (device for the autonomous bootstrapping of unified sentience).

The graph represents a network of 6,501 Twitter users whose tweets in the requested range contained "chatbot", or who were replied to or mentioned in those tweets. The network was obtained from the NodeXL Graph Server on Friday, 28 January 2022 at 13:30 UTC. The requested start date was Friday, 28 January 2022 at 01:01 UTC and the maximum number of tweets (going backward in time) was 7,500. The tweets in the network were tweeted over the 7-day, 17-hour, 41-minute period from Thursday, 20 January 2022 at 07:18 UTC to Friday, 28 January 2022 at 01:00 UTC. Additional tweets that were mentioned in this data set were also collected from prior time periods.

Aqueous hydrolysis is used to chemically recycle polyethylene terephthalate (PET) due to the production of high-quality terephthalic acid (TPA), the PET monomer. PET hydrolysis depends on various reaction conditions including PET size, catalyst concentration, reaction temperature, etc. So, modeling PET hydrolysis by considering the effective factors can provide useful information for material scientists to specify how to design and run these reactions. It will save time, energy, and materials by optimizing the hydrolysis conditions. Machine learning algorithms enable to design models to predict output results. For the first time, 381 experimental data were gathered to model the aqueous hydrolysis of PET. Effective reaction conditions on PET hydrolysis were connected to TPA yield. The logistic regression was applied to rank the reaction conditions. Two algorithms were proposed, artificial neural network multilayer perceptron (ANN-MLP) and adaptive network-based fuzzy inference system (ANFIS). The dataset was divided into training and testing sets to train and test the models, respectively. The models predicted TPA yield sufficiently where the ANFIS model outperformed. R-squared (R2) and Root Mean Square Error (RMSE) loss functions were employed to measure the efficiency of the models and evaluate their performance.

Pedestrian crossing prediction has been a topic of active research, resulting in many new algorithmic solutions. While measuring the overall progress of those solutions over time tends to be more and more established due to the new publicly available benchmark and standardized evaluation procedures, knowing how well existing predictors react to unseen data remains an unanswered question. This evaluation is imperative as serviceable crossing behavior predictors should be set to work in various scenarii without compromising pedestrian safety due to misprediction. To this end, we conduct a study based on direct cross-dataset evaluation. Our experiments show that current state-of-the-art pedestrian behavior predictors generalize poorly in cross-dataset evaluation scenarii, regardless of their robustness during a direct training-test set evaluation setting. In the light of what we observe, we argue that the future of pedestrian crossing prediction, e.g. reliable and generalizable implementations, should not be about tailoring models, trained with very little available data, and tested in a classical train-test scenario with the will to infer anything about their behavior in real life. It should be about evaluating models in a cross-dataset setting while considering their uncertainty estimates under domain shift.

A major archetype of artificial intelligence is developing algorithms facilitating temporal efficiency and accuracy while boosting the generalization performance. Even with the latest developments in machine learning, a key limitation has been the inefficient feature extraction from the initial data, which is essential in performance optimization. Here, we introduce a feature extraction method inspired by sensory cortical networks in the brain. Dubbed as bioinspired cortex, the algorithm provides convergence to orthogonal features from streaming signals with superior computational efficiency while processing data in compressed form. We demonstrate the performance of the new algorithm using artificially created complex data by comparing it with the commonly used traditional clustering algorithms, such as Birch, GMM, and K-means. While the data processing time is significantly reduced, seconds versus hours, encoding distortions remain essentially the same in the new algorithm providing a basis for better generalization. Although we show herein the superior performance of the cortex model in clustering and vector quantization, it also provides potent implementation opportunities for machine learning fundamental components, such as reasoning, anomaly detection and classification in large scope applications, e.g., finance, cybersecurity, and healthcare.

Breast cancer is in the most common malignant tumor in women. It accounted for 30% of new malignant tumor cases. Although the incidence of breast cancer remains high around the world, the mortality rate has been continuously reduced. This is mainly due to recent developments in molecular biology technology and improved level of comprehensive diagnosis and standard treatment. Early detection by mammography is an integral part of that. The most common breast abnormalities that may indicate breast cancer are masses and calcifications. Previous detection approaches usually obtain relatively high sensitivity but unsatisfactory specificity. We will investigate an approach that applies the discrete wavelet transform and Fourier transform to parse the images and extracts statistical features that characterize an image's content, such as the mean intensity and the skewness of the intensity. A naive Bayesian classifier uses these features to classify the images. We expect to achieve an optimal high specificity.

Sentiment analysis is one of the most widely studied applications in NLP, but most work focuses on languages with large amounts of data. We introduce the first large-scale human-annotated Twitter sentiment dataset for the four most widely spoken languages in Nigeria (Hausa, Igbo, Nigerian-Pidgin, and Yor\`ub\'a ) consisting of around 30,000 annotated tweets per language (and 14,000 for Nigerian-Pidgin), including a significant fraction of code-mixed tweets. We propose text collection, filtering, processing and labeling methods that enable us to create datasets for these low-resource languages. We evaluate a rangeof pre-trained models and transfer strategies on the dataset. We find that language-specific models and language-adaptivefine-tuning generally perform best. We release the datasets, trained models, sentiment lexicons, and code to incentivizeresearch on sentiment analysis in under-represented languages.

Multi-view learning is frequently used in data science. The pairwise correlation maximization is a classical approach for exploring the consensus of multiple views. Since the pairwise correlation is inherent for two views, the extensions to more views can be diversified and the intrinsic interconnections among views are generally lost. To address this issue, we propose to maximize higher order correlations. This can be formulated as a low rank approximation problem with the higher order correlation tensor of multi-view data. We use the generating polynomial method to solve the low rank approximation problem. Numerical results on real multi-view data demonstrate that this method consistently outperforms prior existing methods.

Google CEO Sundar Pichai said, "Artificial Intelligence is more profound than fire, electricity, or the internet." His words certainly make sense owing to AI's contributions to the world, climate change, space exploration, or developing cancer treatments. The way AI enables machines to make decisions faster with more accuracy than a human mind is truly extraordinary. It indicates the power of AI and how it can unlock unimaginable possibilities in life. With this backdrop in mind, here's a list of top tech trends that businesses must focus on and invest in: AI has been game-changing across various industries.