Náš další technický večer se konal v Národní technické knihovně. Zabýval se výzkumem v oblasti umělé inteligence (AI) pro autonomní řízení, souvisejícimi problémy a výzvami.

Vývoj autonomních vozidel už nepředstavuje hudbu budoucnosti, ale dneška. Začíná boj jak mezi nadnárodními korporáty, menšími společnostmi, tak i univerzitami, kdo dřív dodá bezchybnou technologii. Umělá inteligence začíná být nedílnou součástí všech oblastí našeho života a autonomní auta nejsou vyjímkou.

Datum: Středa 17. 4. 2019

Adresa:

Národní technická knihovna
Technická 2710/6
160 80 Praha
Česká republika

Vchod NTK3

Program:

[17:00] otevíráme
[17:30] prezentace a otevřená diskuse
[20:00] networking a občerstvení

Témata & Přednášející:

Unsupervised domain adaptation with application to urban scene analysis [CS]

Patrick Pérez ředitel Valeo.ai

In numerous real world applications, no matter how much energy is devoted to build real and/or synthetic training datasets, there remains a large distribution gap between these data and those met at run-time. This gap results in severe, possibly catastrophic, performance loss. This problem is especially acute for automated and autonomous driving systems, where generalizing well to diverse testing environments remains a major challenge. One promising tool to mitigate this issue it unsupervised domain adaptation (UDA), which assumes that un-annotated data from the “test domain” are available at training time, along with the annotated data from the “source domain”. We will discuss different ways to approach UDA, with application to semantic segmentation and object detection in urban scenes. We will introduce a new approach, called AdvEnt, that relies on combining adversarial training with minimization of decision entropy (seen as a proxy for uncertainty).[CS]

Designing multimodal deep architectures for Visual Question Answering [CS]

Matthieu Cord profesor na univerzitě Paris Sorbonne a výzkumník ve Valeo.ai

Multimodal representation learning for text and image has been extensively studied in recent years. Currently, one of the most popular tasks in this field is Visual Question Answering (VQA). I will introduce this complex multimodal task, which aims at answering a question about an image. To solve this problem, visual and textual deep nets models are required and, high level interactions between these two modalities have to be carefully designed into the model in order to provide the right answer. This projection from the unimodal spaces to a multimodal one is supposed to extract and model the relevant correlations between the two spaces. Besides, the model must have the ability to understand the full scene, focus its attention on the relevant visual regions and discard the useless information regarding the question. [CS]

Learning for traversing rough terrain [CS]

Tomáš Svoboda docent na Českém vysokém učení technickém, vedoucí katedry kybernetiky

Autonomous traversal of difficult obstacles and rough terrain in general is one of the essential functionalities required for deploying search and rescue robot. The talk will discuss several learning algorithms for controling robot morphology – configuration of articulated parts and their compliance. Algorithms use both interoceptive and exteroceptive data. Our story begins with a classical Reinforcement learning approach and ends with domain transfer by employing generative adversarial models for bridging the gap between simulated and real world. [CS]

Registrer to Newsletter Registrujte se k Newsletteru