Author name cluster

Yoonsuck Choe

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

8 papers

2 author rows

AAAI Conference 2020 Short Paper

Action Recognition and State Change Prediction in a Recipe Understanding Task Using a Lightweight Neural Network Model (Student Abstract)

Qing Wan
Yoonsuck Choe

Consider a natural language sentence describing a speciﬁc step in a food recipe. In such instructions, recognizing actions (such as press, bake, etc.) and the resulting changes in the state of the ingredients (shape molded, custard cooked, temperature hot, etc.) is a challenging task. One way to cope with this challenge is to explicitly model a simulator module that applies actions to entities and predicts the resulting outcome (Bosselut et al. 2018). However, such a model can be unnecessarily complex. In this paper, we propose a simpli- ﬁed neural network model that separates action recognition and state change prediction, while coupling the two through a novel loss function. This allows learning to indirectly in- ﬂuence each other. Our model, although simpler, achieves higher state change prediction performance (67% average accuracy for ours vs. 55% in (Bosselut et al. 2018)) and takes fewer samples to train (10K ours vs. 65K+ by (Bosselut et al. 2018)).

PDF Details

AAAI Conference 2020 Conference Paper

Plug-in, Trainable Gate for Streamlining Arbitrary Neural Networks

Jaedeok Kim
Chiyoun Park
Hyun-Joo Jung
Yoonsuck Choe

Architecture optimization, which is a technique for ﬁnding an efﬁcient neural network that meets certain requirements, generally reduces to a set of multiple-choice selection problems among alternative sub-structures or parameters. The discrete nature of the selection problem, however, makes this optimization difﬁcult. To tackle this problem we introduce a novel concept of a trainable gate function. The trainable gate function, which confers a differentiable property to discretevalued variables, allows us to directly optimize loss functions that include non-differentiable discrete values such as 0-1 selection. The proposed trainable gate can be applied to pruning. Pruning can be carried out simply by appending the proposed trainable gate functions to each intermediate output tensor followed by ﬁne-tuning the overall model, using any gradient-based training methods. So the proposed method can jointly optimize the selection of the pruned channels while ﬁne-tuning the weights of the pruned model at the same time. Our experimental results demonstrate that the proposed method efﬁciently optimizes arbitrary neural networks in various tasks such as image classiﬁcation, style transfer, optical ﬂow estimation, and neural machine translation.

PDF Details

AAAI Conference 2019 Short Paper

Comparing Sample-Wise Learnability across Deep Neural Network Models

Seung-Geon Lee
Jaedeok Kim
Hyun-Joo Jung
Yoonsuck Choe

Estimating the relative importance of each sample in a training set has important practical and theoretical value, such as in importance sampling or curriculum learning. This kind of focus on individual samples invokes the concept of samplewise learnability: How easy is it to correctly learn each sample (cf. PAC learnability)? In this paper, we approach the sample-wise learnability problem within a deep learning context. We propose a measure of the learnability of a sample with a given deep neural network (DNN) model. The basic idea is to train the given model on the training set, and for each sample, aggregate the hits and misses over the entire training epochs. Our experiments show that the samplewise learnability measure collected this way is highly linearly correlated across different DNN models (ResNet-20, VGG-16, and MobileNet), suggesting that such a measure can provide deep general insights on the data’s properties. We expect our method to help develop better curricula for training, and help us better understand the data itself.

PDF Details

EWRL Workshop 2012 Conference Paper

Directed Exploration in Reinforcement Learning with Transferred Knowledge

Timothy A. Mann
Yoonsuck Choe

Experimental results suggest that transfer learning (TL), compared to learning from scratch, can decrease exploration by reinforcement learning (RL) algorithms. Most existing TL algorithms for RL are heuristic and may result in worse performance than learning from scratch (i. e. , negative transfer). We introduce a theoretically grounded and flexible approach that transfers action-values via an intertask mapping and, based on those, explores the target task systematically. We characterize positive transfer as (1) decreasing sample complexity in the target task compared to the sample complexity of the base RL algorithm (without transferred action-values) and (2) guaranteeing that the algorithm converges to a near-optimal policy (i. e. , negligible optimality loss). The sample complexity of our approach is no worse than the base algorithm's, and our analysis reveals that positive transfer can occur even with highly inaccurate and partial intertask mappings. Finally, we empirically test directed exploration with transfer in a multijoint reaching task, which highlights the value of our analysis and the robustness of our approach under imperfect conditions.

Details

AAAI Conference 2011 Conference Paper

Scaling Up Reinforcement Learning through Targeted Exploration

Timothy Mann
Yoonsuck Choe

Recent Reinforcement Learning (RL) algorithms, such as R- MAX, make (with high probability) only a small number of poor decisions. In practice, these algorithms do not scale well as the number of states grows because the algorithms spend too much effort exploring. We introduce an RL algorithm State TArgeted R-MAX (STAR-MAX) that explores a subset of the state space, called the exploration envelope ξ. When ξ equals the total state space, STAR-MAX behaves identically to R-MAX. When ξ is a subset of the state space, to keep exploration within ξ, a recovery rule β is needed. We compared existing algorithms with our algorithm employing various exploration envelopes. With an appropriate choice of ξ, STAR-MAX scales far better than existing RL algorithms as the number of states increases. A possible drawback of our algorithm is its dependence on a good choice of ξ and β. However, we show that an effective recovery rule β can be learned on-line and ξ can be learned from demonstrations. We also ﬁnd that even randomly sampled exploration envelopes can improve cumulative rewards compared to R-MAX. We expect these results to lead to more efﬁcient methods for RL in large-scale problems.

PDF Details

AAAI Conference 2006 Conference Paper

Motion-Based Autonomous Grounding: Inferring External World Properties from Encoded Internal Sensory States Alone

Yoonsuck Choe

How can we build artificial agents that can autonomously explore and understand their environments? An immediate requirement for such an agent is to learn how its own sensory state corresponds to the external world properties: It needs to learn the semantics of its internal state (i. e. , grounding). In principle, we as programmers can provide the agents with the required semantics, but this will compromise the autonomy of the agent. To overcome this problem, we may fall back on natural agents and see how they acquire meaning of their own sensory states, their neural firing patterns. We can learn a lot about what certain neural spikes mean by carefully controlling the input stimulus while observing how the neurons fire. However, neurons embedded in the brain do not have direct access to the outside stimuli, so such a stimulus-to-spike association may not be learnable at all. How then can the brain solve this problem? (We know it does.) We propose that motor interaction with the environment is necessary to overcome this conundrum. Further, we provide a simple yet powerful criterion, sensory invariance, for learning the meaning of sensory states. The basic idea is that a particular form of action sequence that maintains invariance of a sensory state will express the key property of the environmental stimulus that gave rise to the sensory state. Our experiments with a sensorimotor agent trained on natural images show that sensory invariance can indeed serve as a powerful objective for semantic grounding.

PDF Details

IJCAI Conference 1997 Conference Paper

Self-Organization and Segmentation with Laterally Connected Spiking Neurons

Yoonsuck Choe
Risto Miikkulainen

A self-organizing model of spiking neurons with dynamic thresholds and lateral excitatory and inhibitory connections is presented and tested in the image segmentation task. The model integrates two previously separate lines of research in modeling the visual cortex. Laterally connected self-organizing maps have been used to model how afferent structures and lateral connections could self-organize through inputdriven Hebbian adaptation. Spiking neurons with leaky integrator synapses have been used to model image segmentation and binding by synchronization and desynchronization of neuronal activity. Although these approaches differ in how they model the neuron, they have the same overall layout of a laterally connected two-dimensional network. This paper shows how both self-organization and segmentation can be achieved in such a network, thus presenting a unified model of development and functional dynamics in the primary visual cortex.

PDF

NeurIPS Conference 1995 Conference Paper

Laterally Interconnected Self-Organizing Maps in Hand-Written Digit Recognition

Yoonsuck Choe
Joseph Sirosh
Risto Miikkulainen

An application of laterally interconnected self-organizing maps (LISSOM) to handwritten digit recognition is presented. The lat(cid: 173) eral connections learn the correlations of activity between units on the map. The resulting excitatory connections focus the activity into local patches and the inhibitory connections decorrelate redun(cid: 173) dant activity on the map. The map thus forms internal representa(cid: 173) tions that are easy to recognize with e. g. a perceptron network. The recognition rate on a subset of NIST database 3 is 4. 0% higher with LISSOM than with a regular Self-Organizing Map (SOM) as the front end, and 15. 8% higher than recognition of raw input bitmaps directly. These results form a promising starting point for building pattern recognition systems with a LISSOM map as a front end.

PDF Details