Learning Statistically Neutral Tasks without Expert Guidance
نویسندگان
چکیده
Eric Postma Computer Science, Universiteit Maastricht, The Netherlands In this paper, we question the necessity of levels of expert-guided abstraction in learning hard, statistically neutral classification tasks. We focus on two tasks, date calculation and parity-12, that are claimed to require intermediate levels of abstraction that must be defined by a human expert. We challenge this claim by demonstrating empirically that a single hidden-layer BP-SOM network can learn both tasks without guidance. Moreover, we analyze the network's solution for the parity-12 task and show that its solution makes use of an elegant intermediary checksum computation.
منابع مشابه
Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning
The ability to act in multiple environments and transfer previous knowledge to new situations can be considered a critical aspect of any intelligent agent. Towards this goal, we define a novel method of multitask and transfer learning that enables an autonomous agent to learn how to behave in multiple tasks simultaneously, and then generalize its knowledge to new domains. This method, termed “A...
متن کاملOnline Multi-Task Learning Using Active Sampling
One of the long-standing challenges in Artificial Intelligence for goal-directed behavior is to build a single agent which can solve multiple tasks. Recent progress in multi-task learning for goal-directed sequential tasks has been in the form of distillation based learning wherein a single student network learns from multiple task-specific expert networks by mimicking the task-specific policie...
متن کاملThe Impact of Structured Input-based Tasks on L2 Learners’ Grammar Learning
Abstract Task-based language teaching has received increased attention in second language research. However, the combination of structured input-based approach and task-based language teaching has not been examined in relation to L2 grammar learning. To address this gap, the present study investigated how the structured input-based tasks with and without explicit information impacted learners’ ...
متن کاملThe Importance of Selective Knowledge Transfer for Lifelong Learning
As knowledge transfer research progresses from single transfer to lifelong learning scenarios, it becomes increasingly important to properly select the source knowledge that would best transfer to the target task. In this position paper, we describe our previous work on selective knowledge transfer and relate it to problems in lifelong learning. We also briefly discuss our ongoing work to devel...
متن کاملThe Impact of Structured Input-based Tasks on L2 Learners’ Grammar Learning
Abstract Task-based language teaching has received increased attention in second language research. However, the combination of structured input-based approach and task-based language teaching has not been examined in relation to L2 grammar learning. To address this gap, the present study investigated how the structured input-based tasks with and without explicit information impacted learners’ ...
متن کامل