[18 October, 11:00] Let's Talk ML

Radek Bartyzal - HOP-Rec: High-Order Proximity for Implicit Recommendation (pdf) (slides)

Two of the most popular approaches to recommender systems are based on factorization and graph-based models. This recent paper introduces a method combining both of these approaches.

Ondra Bíža - Learning Synergies between Pushing and Grasping with Self-supervised Deep Reinforcement Learning (pdf) (slides)

Skilled robotic manipulation benefits from complex synergies between pushing and grasping actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. This paper presents a policy able to learn pushing motions that enable future grasps, while learning grasps that can leverage past pushes.

[2 May, 13:00] Let's Talk ML

Petr Nevyhoštěný - Deep Clustering with Convolutional Autoencoders (slides)

Deep clustering utilizes deep neural networks to learn feature representation that is suitable for clustering tasks. This paper proposes a clustering algorithm that uses convolutional autoencoders to learn embedded features, and then incorporates clustering oriented loss on embedded features to jointly perform feature refinement and cluster assignment.

Václav Ostrožlík - Learning to learn by gradient descent by gradient descent (slides)

We've seen many significant improvements when replacing hand-designed features with learned ones before. However, optimization algorithms are still designed by hand. In this work, authors describe that the optimization algorithm can be seen as learning problem itself allowing to get better performing, specialized optimizer.

[18 April, 13:00] Let's Talk ML

Radek Bartyzal - Adversarial Network Compression (slides)

Knowledge distillation is a method of training a smaller student model using a previously trained larger teacher model to achieve a better classification accuracy than a normally trained student model.
This paper presents a new way of knowledge distillation by leveraging the recent advances in Generative Adversarial Networks.

Ondra Podsztavek - World Models (slides)

The paper explores building generative neural network models of popular reinforcement learning environments. A world model can be trained quickly in an unsupervised manner to learn a compressed spatial and temporal representation of the environment. By using features extracted from the world model as inputs to an agent, it can train a very compact and simple policy that can solve the required task. It can even train an agent entirely inside of its own hallucinated dream generated by its world model, and transfer this policy back into the actual environment.

[4 April, 13:00] Let's Talk ML

Ondra Bíža - Learning to grasp object with convolutional networks (slides)

Precise grasping of objects is essential in many applications of robotics such as assisting patients with motoric impairments. I will compare two approaches to learning how to grasp: Google's large-scale venture and a much smaller project carried out by the Northeastern University, which nevertheless achieved competitive results.

Václav Ostrožlík - Differentiable Neural Computer (slides)

Differentiable neural computer is a model based on neural network controller with external memory that is able to store and navigate complex data on its own. I'll go through its architectural details, compare it with Neural Turing Machines and show some interesting possibilities of using the model.

[21 March, 13:00] Let's Talk ML

Matus Zilinec - Machine text comprehension with BiDAF (slides)

I will talk about the Bi-Directional Attention Flow network for answering questions in natural language about an arbitrary paragraph. BiDAF is a multi-stage process that represents the context at different levels of granularity and uses attention mechanism to obtain a query-aware context representation without early summarization. The model achieves state-of-the-art results in Stanford Question Answering Dataset.

Radek Bartyzal - Objects that sound (slides)

A simple network architecture trained only from video is able to reach impressive results in localization of objects that produce a provided sound in a provided frame. This paper builds on an earlier work called 'Look Listen and Learn' and adds support of cross modal retrieval meaning that it can return an image for a provided sound and vice versa. I will present the new architecture and explain the advantages compared to the previous one.

Follow Us

Copyright (c) Data Science Laboratory @ FIT CTU 2014–2016. All rights reserved.