We propose a hierarchical neural architecture able to recognise observed human actions. Each layer in the architecture represents increasingly complex human activity features. The first layer consists of a SOM which performs dimensionality reduction and clustering of the feature space. It represents the dynamics of the stream of posture frames in action sequences as activity trajectories over time. The second layer in the hierarchy consists of another SOM which clusters the activity trajectories of the first-layer SOM and thus it learns to represent action prototypes independent of how long the activity trajectories last. The third layer of the hierarchy consists of a neural network that learns to label action prototypes of the second-layer SOM and is independent to certain extent of the camera’s angle and relative distance to the actor. The experiments were carried out with encouraging results with action movies taken from the INRIA 4D repository. The architecture correctly recognised 100% of the actions it was trained on, while it exhibited 53% recognition rate when presented with similar actions interpreted and performed by a different actor.

An important part of human intelligence is the ability to use language. Humans learn how to use language in a society of language users, which is probably the most effective way to learn a language from the ground up. Principles that might allow an artificial agents to learn language this way are not known at present. Here we present a framework which begins to address this challenge. Our auto-catalytic, endogenous, reflective architecture (AERA) supports the creation of agents that can learn natural language by observation. We present results from two experiments where our S1 agent learns human communication by observing two humans interacting in a realtime mock television interview, using gesture and situated language. Results show that S1 can learn multimodal complex language and multimodal communicative acts, using a vocabulary of 100 words with numerous sentence formats, by observing unscripted interaction between the humans, with no grammar being provided to it a priori, and only high-level information about the format of the human interaction in the form of high-level goals of the interviewer and interviewee and a small ontology. The agent learns both the pragmatics, semantics, and syntax of complex sentences spoken by the human subjects on the topic of recycling of objects such as aluminum cans, glass bottles, plastic, and wood, as well as use of manual deictic reference and anaphora.

An important part of human intelligence, both historically and operationally, is our ability to communicate. We learn how to communicate, and maintain our communicative skills, in a society of communicators – a highly effective way to reach and maintain proficiency in this complex skill. Principles that might allow artificial agents to learn language this way are in completely known at present – the multi-dimensional nature of socio-communicative skills are beyond every machine learning framework so far proposed. Our work begins to address the challenge of proposing a way for observation-based machine learning of natural language and communication. Our framework can learn complex communicative skills with minimal up-front knowledge. The system learns by incrementally producing predictive models of causal relationships in observed data, guided by goal-inference and reasoning using forward-inverse models. We present results from two experiments where our S1 agent learns human communication by observing two humans interacting in a realtime TV-style interview, using multimodal communicative gesture and situated language to talk about recycling of various materials and objects. S1 can learn multimodal complex language and multimodal communicative acts, a vocabulary of 100 words forming natural sentences with relatively complex sentence structure, including manual deictic reference and anaphora. S1 is seeded only with high-level information about goals of the interviewer and interviewee, and a small ontology; no grammar or other information is provided to S1 a priori. The agent learns the pragmatics, semantics, and syntax of complex utterances spoken and gestures from scratch, by observing the humans compare and contrast the cost and pollution related to recycling aluminum cans, glass bottles, newspaper, plastic, and wood. After 20 hours of observation S1 can perform an unscripted TV interview with a human, in the same style, without making mistakes.

Existing methods for security risk analysis typically estimate time, cost, or likelihood of success of attack steps. When the threat environment changes, such values have to be updated as well. However, the estimated values reflect both system properties and attacker properties: the time required for an attack step depends on attacker skill as well as the strength of a particular system component. In the TRESPASS project, we propose the separation of attacker and system properties. By doing so, we enable “plug-and-play” attacker profiles: profiles of adversaries that are independent of system properties, and thus can be reused in the same or different organisation to compare risk in case of different attacker profiles. We demonstrate its application in the framework of attack trees, as well as our new concept of attack navigators.