[SAIF 2019] Day2: Geometric Deep Learning for Forecasting and Semi-supervised Learning – Joan Bruna

Posted by

Geometric Deep Learning is an emerging paradigm to process graph-structured data with end-to-end trainable models, Graph Neural Networks (GNNs), with the ability to leverage prior knowledge about the data domain while offering large expressive power. Such attractive tradeoff has resulted in state-of-the-art performance over diverse domains, ranging from social networks, biology, knowledge bases, or finance. In this talk, I will present recent advances in our group covering both theory and applications. On the theory side, we quantify both the approximation power of GNN architectures and their stability to graph perturbations, resulting in a principled architecture design. We will illustrate these theoretical advances with applications in semi-supervised learning and forecasting in dynamic graphs modeling Social Network data, and discuss broader applications to recommender systems and fraud detection.... Read More إقرأ المزيد | Share it now!

[SAIF 2019] Day 2: Symbolic Logic meets Machine Learning: Towards Reliable AI – Vaishak Belle

Posted by

Artificial Intelligence (AI) provides many opportunities to improve private and public life, and it has enjoyed significant investment. Indeed, discovering patterns and structures in large troves of data in an automated manner is a core component of data science. Machine learning currently drives applications in computational biology, natural language processing and robotics. However, such a highly positive impact is coupled with a significant challenge: when can we convincingly deploy these methods in our workplace? For example, can we provide prior knowledge and suggestions to the learning modules? Can we learn interpretable symbolic structures from data? In this talk, we look at the fundamental problem of unifying reasoning and learning, and how this enables a systematic way to integrate human knowledge and data-driven learning methods. We will then briefly consider how that unification may help us take steps towards a commonsensical, transparent and responsible AI.... Read More إقرأ المزيد | Share it now!

[SAIF 2019] Day 2: Rational Recurrences for Empirical Natural Language Processing – Noah Smith

Posted by

Despite their often-discussed advantages, deep learning methods largely disregard theories of both learning and language. This makes their prediction behavior hard to understand and explain. In this talk, I will present a path toward more understandable (but still “deep”) natural language processing models, without sacrificing accuracy. Rational recurrences comprise a family of recurrent neural networks that obey a particular set of rules about how to calculate hidden states, and hence correspond to parallelized weighted finite-state pattern matching. Many recently introduced models turn out to be members of this family, and the weighted finite-state view lets us derive some new ones. I’ll introduce rational RNNs and present some of the ways we have used them in NLP. My collaborators on this work include Jesse Dodge, Hao Peng, Roy Schwartz, and Sam Thomson. ... Read More إقرأ المزيد | Share it now!

[SAIF 2019] Day 2: Supersizing and Empowering Visual and Robot Learning – Abhinav Gupta│Samsung

Posted by

Supersizing and Empowering Visual and Robot Learning Abstract: In the last decade, we have made significant advances in the field of computer vision thanks to supervised learning. But this passive supervision of our models has now become our biggest bottleneck. In this talk, I will discuss our efforts towards scaling up and empowering visual learning. First, I will show how the amount of labeled data is a crucial factor in learning. I will then describe how we can overcome the passive supervision bottleneck by self-supervised learning. Next, I will discuss how embodiment is crucial for learning – our agents live in the physical world and need the ability to interact in the physical world. Towards this goal, I will finally present our efforts in large-scale learning of embodied agents in robotics. Finally, I will discuss how we can move from passive supervision to active exploration – the ability of agents to create their own training data. ... Read More إقرأ المزيد | Share it now!