The hype around delivery robots has fizzled, but DoorDash is still determined to launch Dot, an adorable red bot. It can ride on roads and in bike lanes, where it will face daunting challenges. DoorDash's new delivery robot is named Dot. When we first got close to Dot, DoorDash's new delivery robot, we looked right into its big blue, pixelated eyes and gave it a kick. It's not WIRED's policy to be mean to 350-pound hunks of plastic on wheels.

In this paper, we study the challenging problem of tracking the trajectory of a moving object in a video with possibly very complex background. In contrast to most existing trackers which only learn the appearance of the tracked object online, we take a different approach, inspired by recent advances in deep learning architectures, by putting more emphasis on the (unsupervised) feature learning problem. Specifically, by using auxiliary natural images, we train a stacked denoising autoencoder offline to learn generic image features that are more robust against variations. This is then followed by knowledge transfer from offline training to the online tracking process. Online tracking involves a classification neural network which is constructed from the encoder part of the trained autoencoder as a feature extractor and an additional classification layer. Both the feature extractor and the classifier can be further tuned to adapt to appearance changes of the moving object. Comparison with the state-of-the-art trackers on some challenging benchmark video sequences shows that our deep learning tracker is very efficient as well as more accurate.

Automatic music recommendation has become an increasingly relevant problem in recent years, since a lot of music is now sold and consumed digitally. Most recommender systems rely on collaborative filtering. However, this approach suffers from the cold start problem: it fails when no usage data is available, so it is not effective for recommending new and unpopular songs. In this paper, we propose to use a latent factor model for recommendation, and predict the latent factors from music audio when they cannot be obtained from usage data. We compare a traditional approach using a bag-of-words representation of the audio signals with deep convolutional neural networks, and evaluate the predictions quantitatively and qualitatively on the Million Song Dataset. We show that using predicted latent factors produces sensible recommendations, despite the fact that there is a large semantic gap between the characteristics of a song that affect user preference and the corresponding audio signal. We also show that recent advances in deep learning translate very well to the music recommendation setting, with deep convolutional neural networks significantly outperforming the traditional approach.

Designing a principled and effective algorithm for learning deep architectures is a challenging problem. The current approach involves two training phases: a fully unsupervised learning followed by a strongly discriminative optimization. We suggest a deep learning strategy that bridges the gap between the two phases, resulting in a three-phase learning procedure. We propose to implement the scheme using a method to regularize deep belief networks with top-down information. The network is constructed from building blocks of restricted Boltzmann machines learned by combining bottom-up and top-down sampled signals. A global optimization procedure that merges samples from a forward bottom-up pass and a top-down pass is used.

Many machine learning problems can be interpreted as learning for matching two types of objects (e.g., images and captions, users and products, queries and documents). The matching level of two objects is usually measured as the inner product in a certain feature space, while the modeling effort focuses on mapping of objects from the original space to the feature space. This schema, although proven successful on a range of matching tasks, is insufficient for capturing the rich structure in the matching process of more complicated objects. In this paper, we propose a new deep architecture to more effectively model the complicated matching relations between two objects from heterogeneous domains. More specifically, we apply this model to matching tasks in natural language, e.g., finding sensible responses for a tweet, or relevant answers to a given question. This new architecture naturally combines the localness and hierarchy intrinsic to the natural language problems, and therefore greatly improves upon the state-of-the-art models.

Plus: America's first AI law is here Scientists can see Earth's permafrost thawing from space Something is rotten in the city of Nunapitchuk. In recent years, sewage has leached into the earth. The ground can feel squishy, sodden. This small town in northern Alaska is experiencing a sometimes overlooked consequence of climate change: thawing permafrost. And Nunapitchuk is far from the only Arctic town to find itself in such a predicament. Now scientists think they may be able to use satellite data to delve deep beneath the ground's surface and get a better understanding of how the permafrost thaws, and which areas might be most severely affected.

We demonstrate that there is significant redundancy in the parameterization of several deep learning models. Given only a few weight values for each feature it is possible to accurately predict the remaining values. Moreover, we show that not only can the parameter values be predicted, but many of them need not be learned at all. We train several different architectures by learning only a small number of weights and predicting the rest. In the best case we are able to predict more than 95% of the weights of a network without any drop in accuracy.

Welcome back to, TIME's new twice-weekly newsletter about AI. If you're reading this in your browser, why not subscribe to have the next one delivered straight to your inbox? A major AI-enabled disaster is becoming increasingly likely as AI capabilities advance. But a new report from a London-based think tank warns that the British government does not have the emergency powers necessary to respond to AI-enabled disasters like the disruption of critical infrastructure or a terrorist attack. The U.K. must give its officials new powers including being able to compel tech companies to share information and restrict public access to their AI models in an emergency, argues the report, which was shared exclusively with TIME ahead of its publication on Tuesday by the Centre for Long-Term Resilience (CLTR).

Recently, it was shown that by dropping out hidden activities with a probability of 0.5, deep neural networks can perform very well. We describe a model in which a binary belief network is overlaid on a neural network and is used to decrease the information content of its hidden units by selectively setting activities to zero. This ''dropout network can be trained jointly with the neural network by approximately computing local expectations of binary dropout variables, computing derivatives using back-propagation, and using stochastic gradient descent. Interestingly, experiments show that the learnt dropout network parameters recapitulate the neural network parameters, suggesting that a good dropout network regularizes activities according to magnitude. When evaluated on the MNIST and NORB datasets, we found our method can be used to achieve lower classification error rates than other feather learning methods, including standard dropout, denoising auto-encoders, and restricted Boltzmann machines. For example, our model achieves 5.8% error on the NORB test set, which is better than state-of-the-art results obtained using convolutional architectures.

'Digital minds will be participants in the social contract that forms the bedrock of human society.' 'Digital minds will be participants in the social contract that forms the bedrock of human society.' It's time to prepare for AI personhood Technological advances will bring social upheaval. How will we treat digital minds, and how will they treat us? L ast month, when OpenAI released its long-awaited chatbot GPT-5, it briefly removed access to a previous chatbot, GPT-4o. Despite the upgrade, users flocked to social media to express confusion, outrage and depression.