We propose a generic framework to calibrate accuracy and confidence (score) of a prediction through stochastic inferences in deep neural networks. We first analyze relation between variation of multiple model parameters for a single example inference and variance of the corresponding prediction scores by Bayesian modeling of stochastic regularization. Our empirical observation shows that accuracy and score of a prediction are highly correlated with variance of multiple stochastic inferences given by stochastic depth or dropout. Motivated by these facts, we design a novel variance-weighted confidence-integrated loss function that is composed of two cross-entropy loss terms with respect to ground-truth and uniform distribution, which are balanced by variance of stochastic prediction scores. The proposed loss function enables us to learn deep neural networks that predict confidence calibrated scores using a single inference. Our algorithm presents outstanding confidence calibration performance and improves classification accuracy with two popular stochastic regularization techniques---stochastic depth and dropout---in multiple models and datasets; it alleviates overconfidence issue in deep neural networks significantly by training networks to achieve prediction accuracy proportional to confidence of prediction.

In this paper, we present a deep reinforcement learning method for quadcopter bypassing the obstacle on the flying path. In the past study, the algorithm only controls the forward direction about quadcopter. In this letter, we use two functions to control quadcopter. One is quadcopter navigating function. It is based on calculating coordination point and find the straight path to the goal. The other function is collision avoidance function. It is implemented by deep Q-network model. Both two function will output rotating degree, the agent will combine both output and turn direct. Besides, deep Q-network can also make quadcopter fly up and down to bypass the obstacle and arrive at the goal. Our experimental result shows that the collision rate is 14% after 500 flights. Based on this work, we will train more complex sense and transfer model to the real quadcopter.

We introduce a new scene graph generation method called image-level attentional context modeling (ILAC). Our model includes an attentional graph network that effectively propagates contextual information across the graph using image-level features. Whereas previous works use an object-centric context, we build an image-level context agent to encode the scene properties. The proposed method comprises a single-stream network that iteratively refines the scene graph with a nested graph neural network. We demonstrate that our approach achieves competitive performance with the state-of-the-art for scene graph generation on the Visual Genome dataset, while requiring fewer parameters than other methods. We also show that ILAC can improve regular object detectors by incorporating relational image-level information.

Neural networks have shown great performance in cognitive tasks. When deploying network models on mobile devices with limited resources, weight quantization has been widely adopted. Binary quantization obtains the highest compression but usually results in big accuracy drop. In practice, 8-bit or 16-bit quantization is often used aiming at maintaining the same accuracy as the original 32-bit precision. We observe different quantization schemes have different accuracy impact on different layers. Thus judiciously selecting different precision for different layers/structures can potentially produce more efficient models compared to traditional quantization methods by striking a better balance between accuracy and compression rate. In this work, we propose a fine-grained quantization approach for deep neural network compression by relaxing the search space of quantization bitwidth from discrete to a continuous domain. The proposed approach applies gradient descend based optimization to generate a mixed-precision quantization scheme that outperforms the accuracy of traditional quantization methods under the same compression rate.

What's more, even AIs based on mechanisms inspired by human biology, such as neural networks, have only a distant relationship with biological neurons in the brain. NN are examples more of the importance of reinforcement and self-organisation of controller networks than any similarity with biology. The first, naive, approach to AI is to think that it is necessary to create a synthetic human, or a synthetic brain to produce cognition: in fact, cognition does not need to be anthropomorphic at all. Second attempt at a definition: "The ability of a machine to achieve performance equal to or better than certain human cognitive processes." This definition is based on the final outcome, without presupposing imitation of biological mechanisms.

Humanity at a Crossroads--Artificial Intelligence is one of the most intriguing topics today, filled with various arguments and views on whether it's a blessing or a threat to humanity. We might be at the crossroads, but what if AI itself is already crossing the line? If we look at "I, Robot," a sci-fi film that takes place in Chicago circa 2035, highly intelligent robots powered by artificial intelligence fill public service positions and have taken over all the menial jobs, including garbage collection, cooking, and even dog walking throughout the world. The movie came out in 2004 starring Will Smith as Detective Del Spooner who eventually discovers a conspiracy in which AI-powered robots may enslave and hurt the human race. Stephen Hawking, famed physicist, also once said: "Success in creating effective AI could be the biggest event in the history of our civilization. So we can't know for sure if we'll be infinitely helped by AI, or ignored by it and side-lined, or conceivably destroyed by it."

What the fund does It invests in companies developing artificial intelligence systems. AI is used in everything from farming, where technology can tell which fruit are ripe enough to pick, to quality control on manufacturing lines, such as detecting whether there are enough toppings on frozen pizzas. What it invests in While about half the fund's investments are in the US, it also holds Japanese, Chinese and Italian stocks. Top holdings include the US credit reporting agency TransUnion, the German software business SAP and Japan's Keyence, which makes sensors and barcode readers. Performance The fund was launched a year ago and has delivered a return of 14.3% since then.

China's Xinhua news agency has become the first to receive a virtual news anchor for its TV channel, and it looks quite real. The news anchor is a male that has been modeled after one of the male news anchors at Xinhua news agency. And the virtual anchor can read the the news as text entered by the news agency. The virtual anchor has human like facial expressions, and reads the news in a synthesized voice that makes it more plausible than anything before. This news anchor was created by the Xinhua news agency of China in collaboration with the Chinese search engine company Sogou.

Imagine a country with an army of techies, a government that supports AI and blockchain by setting a mandate and investing billions, large scale tech companies that are rapidly experimenting and implementing at scale, and an abundance of data to feed the application of these technologies. This just about covers the AI and blockchain playground that is China. The gloves are off, and over the coming years some of the greatest advancements will emanate from the east. An ambitious AI strategic plan was laid by the China's State Council in July 2017, aiming to create a domestic 1 trillion yuan ($150 billion) AI industry by 2030. Following this, Chinese president Xi Jinping called upon his country to take the lead in developing new technologies like artificial intelligence, the internet of things, and blockchain.

Chinese tech leaders articulated their vision for the post-internet future at the World Internet Conference held this past week, with artificial intelligence, complete digitisation of the economy and a call for more basic science being among the topics of discussion – though it was mostly a local affair with the absence of high profile US tech company representatives amid the ongoing US-China trade war. "Artificial intelligence and the internet represent two different eras," said Baidu CEO Robin Li Yanhong on Thursday. "We will step into the AI era in the coming three to five decades while the previous 20 years belonged to internet." Baidu, which operates China's largest internet search engine, is a so-called AI national champion with its efforts in the field endorsed by the central government. It was also the first Chinese company to join an international AI ethics group set up last month, alongside members such as Apple and Alphabet's Google.