`

Timezone: »

 
Workshop
BabyMind: How Babies Learn and How Machines Can Imitate
Byoung-Tak Zhang · Gary Marcus · Angelo Cangelosi · Pia Knoeferle · Klaus Obermayer · David Vernon · Chen Yu

Fri Dec 11 08:40 AM -- 05:30 PM (PST) @ None
Event URL: https://babymind-workshop-2020.github.io/ »

Deep neural network models have shown remarkable performance in tasks such as visual object recognition, speech recognition, and autonomous robot control. We have seen continuous improvements throughout the years which have led to these models surpassing human performance in a variety of tasks such as image classification, video games, and board games. However, the performance of deep learning models heavily relies on a massive amount of data, which requires huge time and effort to collect and label them.

Recently, to overcome these weaknesses and limitations, attention has shifted towards machine learning paradigms such as semi-supervised learning, incremental learning, and meta-learning which aim to be more data-efficient. However, these learning models still require a huge amount of data to achieve high performance on real-world problems. There has been only a few achievement or breakthrough, especially in terms of the ability to grasp abstract concepts and to generalize problems.

In contrast, human babies gradually make sense of the environment through their experiences, a process known as learning by doing, without a large amount of labeled data. They actively engage with their surroundings and explore the world through their own interactions. They gradually acquire the abstract concept of objects and develop the ability to generalize problems. Thus, if we understand how a baby's mind develops, we can imitate those learning processes in machines and thereby solve previously unsolved problems such as domain generalization and overcoming the stability-plasticity dilemma. In this workshop, we explore how these learning mechanisms can help us build human-level intelligence in machines.

In this interdisciplinary workshop, we bring together eminent researchers in Computer Science, Cognitive Science, Psychology, Brain Science, Developmental Robotics and various other related fields to discuss the below questions on babies vs. machines.

■ How far is the state-of-the-art machine intelligence from babies?
■ How does a baby learn from their own interactions and experiences?
■ What sort of insights can we acquire from the baby's mind?
■ How can those insights help us build smart machines with baby-like intelligence?
■ How can machines learn from babies to do better?
■ How can these machines further contribute to solving the real-world problems?

We will invite selected experts in the related fields to give insightful talks. We will also encourage interdisciplinary contributions from researchers in the above topics. Hence, we expect this workshop to be a good starting point for participants in various fields to discuss theoretical fundamentals, open problems, and major directions of further development in an exciting new area.

Fri 8:40 a.m. - 9:00 a.m.
Opening Remarks: BabyMind, Byoung-Tak Zhang and Gary Marcus (Opening Remarks)  link » Byoung-Tak Zhang, Gary Marcus
Fri 9:00 a.m. - 9:40 a.m.
  

Celeste Kidd (University of California, Berkeley)

Celeste Kidd
Fri 9:40 a.m. - 10:20 a.m.
  

Oliver Brock (Technical University of Berlin)

Oliver Brock
Fri 10:20 a.m. - 10:45 a.m.
Coffee Break (Break)
Fri 10:45 a.m. - 11:00 a.m.
Contributed Talk: Automatic Recall Machines: Internal Replay, Continual Learning and the Brain (Talk)   
Xu Ji
Fri 11:00 a.m. - 11:15 a.m.
Contributed Talk: Architecture Agnostic Neural Networks (Talk)   
Sabera Talukder
Fri 11:15 a.m. - 11:30 a.m.
Contributed Talk: Human-Like Active Learning: Machines Simulating Human Learning Process (Talk)   
Jaeseo Lim
Fri 11:30 a.m. - 12:30 p.m.
Poster Session (Poster)  link »
Kwanyoung Park, Haizi Yu, Alban Laflaquière, Yizhou Zhang, Hugo Caselles-Dupré, Charlie Snell, Phil Ball, Jhoseph Shin, Jelena Sucevic, Kezhen Chen, Won-Seok Choi, Eon-Suk Ko, Xu Ji
Fri 12:30 p.m. - 1:30 p.m.
Lunch Break (Break)
Fri 1:30 p.m. - 1:45 p.m.
Contributed Talk: What can babies teach us about contrastive methods? (Talk)   
Jelena Sucevic
Fri 1:45 p.m. - 2:00 p.m.
Contributed Talk: Learning Canonical Transformations (Talk)   
Zack Dulberg
Fri 2:00 p.m. - 2:15 p.m.
Contributed Talk: Modeling Social Interaction for Baby in Simulated Environment for Developmental Robotics (Talk)   
Deokgun Park
Fri 2:15 p.m. - 2:30 p.m.
Contributed Talk: ARLET: Adaptive Representation Learning with End-to-end Training (Talk)   
Won-Seok Choi
Fri 2:30 p.m. - 2:45 p.m.
Contributed Talk: Not all input is equal: the efficacy of book reading in infants' word learning is mediated by child-directed speech (Talk)   
Eon-Suk Ko
Fri 2:45 p.m. - 3:30 p.m.
Coffee Break & Poster Session (Poster)  link »
Fri 3:30 p.m. - 4:10 p.m.
  

Angelo Cangelosi

Angelo Cangelosi
Fri 4:10 p.m. - 4:50 p.m.

Josh Tenenbaum (Massachusetts Institute of Technology)

Josh Tenenbaum
Fri 4:50 p.m. - 5:30 p.m.
Panel Discussion

Author Information

Byoung-Tak Zhang (Seoul National University & Surromind Robotics)
Gary Marcus (New York University)
Angelo Cangelosi (University of Manchester)
Pia Knoeferle (Humboldt University of Berlin)
Klaus Obermayer (Technical University Berlin)
David Vernon (Carnegie Mellon University Africa)
Chen Yu (Indiana University)

More from the Same Authors