Effective data management is crucial for organizations of all sizes and in all industries because it helps ensure the accuracy, security, and accessibility of data, which is essential for making good decisions and operating efficiently. Properly organizing and maintaining your data can help ensure that it is accurate and up to date. This is important because inaccurate data can lead to incorrect conclusions and poor decision-making. Well-managed data is easier to access and use, which can help you save time and reduce the risk of errors. In some cases, proper data management is required by law, such as the General Data Protection Regulation (GDPR) in the European Union. Database management system vendors are now deploying artificial intelligence, particularly machine learning, into the database itself.

The purpose of Computer Vision (CV) is to allow machines to obtain valuable information from their surroundings, by analyzing visual data that can be provided by different sources such as digital images and videos. The nature of such information depends on the final goal of the machine. Think, for example, of self-driving cars. A CV module that is capable of detecting in real-time objects that appear in front of the car is essential to avoid accidents. On the other hand, a robot that has to give directions to people inside a railway station can change the way of speaking based on whether the listener is a child or an adult.

The'planning as inference' paradigm extends Bayesian inference to future observations. The agent in the environment is modelled as a Bayesian generative model, but the belief about the distribution of agent's actions is updated based on future goals rather than on past facts. This allows to use common modelling and inference tools, notably probabilistic programming, to represent computer agents and explore their behavior. Representing agents as general programs provides flexibility compared to restricted approaches, such as Markov decision processes and their variants and extensions, and allows to model a broad range of complex behaviors in a unified and natural way. Planning as inference models agent preferences through conditioning agents on preferred future behaviors. Often, the conditioning is achieved through the Boltzmann distribution: the probability of a realization of agent's behavior is proportional to the exponent of the agent's reward. The motivation of using the Boltzmann distribution is not clear though. A'rational' agent should behave in a way that maximizes the agent's expected utility, shouldn't it? One argument is that the Boltzmann distribution models human errors and irrationality.

Facebook's exceptionally deep pockets allow the company to fund all manner of innovative product development. One leading area of development for the company is artificial intelligence, which has long been a dream confined to the realm of science fiction. Yet, Facebook's AI was so advanced that it created its own language. This development was unexpected, and the researchers building the program pulled the plug, killing the program. The media has played this up like a science fiction movie.

Last week I read Abadi and Andersen's recent paper [1], Learning to Protect Communications with Adversarial Neural Cryptography. I thought the idea seemed pretty cool and that it wouldn't be too tricky to implement, and would also serve as an ideal project to learn a bit more Theano. This post describes the paper, my implementation, and the results. The authors set up their experiment as follows. We have three neural networks, named Alice, Bob, and Eve.

Last week I read Abadi and Andersen's recent paper [1], Learning to Protect Communications with Adversarial Neural Cryptography. I thought the idea seemed pretty cool and that it wouldn't be too tricky to implement, and would also serve as an ideal project to learn a bit more Theano. This post describes the paper, my implementation, and the results. The authors set up their experiment as follows. We have three neural networks, named Alice, Bob, and Eve.

What happens when you tell two smart computers to talk to each other in secret and task another AI with breaking that conversation? You get one of the coolest experiments in cryptography I've seen in a while. In short, Google Brain researchers have discovered that the AI, when properly tasked, create oddly inhuman cryptographic schemes and that they're better at encrypting than decrypting. The paper, "Learning to protect communications with adversarial neural cryptography," is available here. The rules of the task were simple.

Google has built machine learning systems that can create their own cryptographic algorithms -- the latest success for AI's use in cybersecurity. But what are the implications of our digital security increasingly being handed over to intelligent machines? Google Brain, the company's California-based AI unit, managed the recent feat by pitting neural networks against each other. Two systems, called Bob and Alice, were tasked with keeping their messages secret from a third, called Eve. None were told how to encrypt messages, but Bob and Alice were given a shared security key that Eve didn't have access too.

What happens when you tell two smart computers to talk to each other in secret and task another AI with breaking that conversation? You get one of the coolest experiments in cryptography I've seen in a while. In short, Google Brain researchers have discovered that the AI, when properly tasked, create oddly inhuman cryptographic schemes and that they're better at encrypting than decrypting. The paper, "Learning to protect communications with adversarial neural cryptography," is available here. The rules of the task were simple.

Intentions have been widely studied in AI, both in the context of decision-making within individual agents and in multi-agent systems. Work on intentions in multi-agent systems has focused on joint intention models, which characterise the mental state of agents with a shared goal engaged in teamwork. In the absence of shared goals, however, intentions play another crucial role in multi-agent activity: they provide a basis around which agents can mutually coordinate activities. Models based on shared goals do not attempt to account for or explain this role of intentions. In this paper, we present a formal model of multi-agent systems in which belief-desire-intention agents choose their intentions taking into account the intentions of others. To understand rational mental states in such a setting, we formally define and investigate notions of multi-agent intention equilibrium, which are related to equilibrium concepts in game theory.