Accident detection is a vital part of traffic safety . Many road users suffer from traffic accidents, as well as their consequences such as delay, congestion, air pollu tion, and so on . In this study, we utilize two advanced deep learning techniques, Long Short - Term Memory (LSTM) and Gated Recurrent Units (GRU s), to detect traffic accidents in Chicago . These two techniques are selected because they are known to perform we ll with sequential data (i.e., time series). The full dataset consists of 241 accident and 6, 038 non - accident cases selected from Chicago expressway, and it includes traffic spatiotemporal data, weather condition data, and congestion status data . Moreover, b ecause the dataset is imbala nced (i.e., the dataset contains many more non - accident cases t han accident cases), Synthetic Minority Over - sampling Technique (SMOTE) is employed . Overall, the two models perform significantly well, both with an Area Under Curve (AUC) of 0.85. Nonetheless, the GRU model is observed to perform slightly better than LSTM model with respect to detection rate . The performance of both models is similar in terms of false alarm rate.

An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Tagging, or using gates, has been used to enable translation models to distinguish between synthetic and natural data. This improves standard back-translation and also enables the use of iterative back-translation on language pairs that underperformed using standard back-translation. This work presents a simplified approach of differentiating between the two data using pretraining and finetuning. The approach - tag-less back-translation - trains the model on the synthetic data and finetunes it on the natural data. Preliminary experiments have shown the approach to continuously outperform the tagging approach on low resource English-Vietnamese neural machine translation. While the need for tagging (noising) the dataset has been removed, the approach outperformed the tagged back-translation approach by an average of 0.4 BLEU.

Flow prediction (e.g., crowd flow, traffic flow) with features of spatial-temporal is increasingly investigated in AI research field. It is very challenging due to the complicated spatial dependencies between different locations and dynamic temporal dependencies among different time intervals. Although measurements of both dependencies are employed, existing methods suffer from the following two problems. First, the temporal dependencies are measured either uniformly or bias against long-term dependencies, which overlooks the distinctive impacts of short-term and long-term temporal dependencies. Second, the existing methods capture spatial and temporal dependencies independently, which wrongly assumes that the correlations between these dependencies are weak and ignores the complicated mutual influences between them. To address these issues, we propose a Spatial-Temporal Self-Attention Network (ST-SAN). As the path-length of attending long-term dependency is shorter in the self-attention mechanism, the vanishing of long-term temporal dependencies is prevented. In addition, since our model relies solely on attention mechanisms, the spatial and temporal dependencies can be simultaneously measured. Experimental results on real-world data demonstrate that, in comparison with state-of-the-art methods, our model reduces the root mean square errors by 9% in inflow prediction and 4% in outflow prediction on Taxi-NYC data, which is very significant compared to the previous improvement.

Large transformer-based language models (LMs) trained on huge text corpora have shown unparalleled generation capabilities. However, controlling attributes of the generated language (e.g. switching topic or sentiment) is difficult without modifying the model architecture or fine-tuning on attribute-specific data and entailing the significant cost of retraining. We propose a simple alternative: the Plug and Play Language Model (PPLM) for controllable language generation, which combines a pretrained LM with one or more simple attribute classifiers that guide text generation without any further training of the LM. In the canonical scenario we present, the attribute models are simple classifiers consisting of a user-specified bag of words or a single learned layer with 100,000 times fewer parameters than the LM. Sampling entails a forward and backward pass in which gradients from the attribute model push the LM's hidden activations and thus guide the generation. Model samples demonstrate control over a range of topics and sentiment styles, and extensive automated and human annotated evaluations show attribute alignment and fluency. PPLMs are flexible in that any combination of differentiable attribute models may be used to steer text generation, which will allow for diverse and creative applications beyond the examples given in this paper.

A lot of the core tech of self-driving cars uses a type of machine learning called deep learning so I've been working with it the past few years.

Socher also teaches computer science at Stanford, where he got his PhD with a focus on AI and deep learning. "I think the future is a fully immersive …

Let's say I am given an Excel sheet with data about various fruits and I have to tell which look like Apples. What I will do is ask a question "Which fruits are red and round?" and divide all fruits which answer yes and no to the question. Now, All Red and Round fruits might not be apples and all apples won't be red and round. So I will ask a question "Which fruits have red or yellow color hints on them? " on red and round fruits and will ask "Which fruits are green and round?" on not red and round fruits. Based on these questions I can tell with considerable accuracy which are apples. This cascade of questions is what a decision tree is. However, this is a decision tree based on my intuition.

An application with 95 percent accuracy may not behave much more differently than one with 96 percent accuracy. They are too expensive to train, too big to fit onto consumer devices, and too slow to be useful to users. In the research phase, you often do not care about the size of the model – but in real life you do. On what factors do you choose the baseline and how do you quantify it? Most of the time, in production, they are only useful if their performance is unquestionably superior.

Having an MRI scan can be an unpleasant experience. The procedure often involves a patient lying down inside a large tube for at least 30 minutes and being instructed to remain motionless as magnetic and radio waves create detailed pictures of their organs. Many find the machine's loud, clanging noises unnerving and are left feeling panicky and claustrophobic. An approach created by Puyang Wang, a doctoral degree candidate in electrical and computer engineering at Johns Hopkins University's Whiting School of Engineering, could help provide some relief. The solution, an algorithm that speeds up MRI data acquisition and results in clearer images, was among the projects recognized at the fastMRI competition held earlier this month by Facebook AI and New York University's Langone Health.