Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 5 of 5
Full-Text Articles in Engineering
Gpu Utilization: Predictive Sarimax Time Series Analysis, Dorothy Dorie Parry
Gpu Utilization: Predictive Sarimax Time Series Analysis, Dorothy Dorie Parry
Modeling, Simulation and Visualization Student Capstone Conference
This work explores collecting performance metrics and leveraging the output for prediction on a memory-intensive parallel image classification algorithm - Inception v3 (or "Inception3"). Experimental results were collected by nvidia-smi on a computational node DGX-1, equipped with eight Tesla V100 Graphic Processing Units (GPUs). Time series analysis was performed on the GPU utilization data taken, for multiple runs, of Inception3’s image classification algorithm (see Figure 1). The time series model applied was Seasonal Autoregressive Integrated Moving Average Exogenous (SARIMAX).
Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher
Reliable Explanations Via Adversarial Examples On Robust Networks, Walt Woods, Jack H. Chen, Christof Teuscher
Student Research Symposium
Neural Networks (NNs) are increasingly used as the basis of advanced machine learning techniques in sensitive fields such as autonomous vehicles and medical imaging. However, NNs have been found vulnerable to a class of imperceptible attacks, called adversarial examples, which arbitrarily alter the output of the network. To close the schism between needing reliability in real-world applications and the fragility of NNs, we propose a new method for stabilizing networks, and show that as an added bonus, our technique results in reliable, high-fidelity explanations for the NN's decision. Compared to the state-of-the-art, this technique increased the area under the curve …
Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher
Explanation Methods For Neural Networks, Jack H. Chen, Christof Teuscher
Student Research Symposium
Neural Networks (NNs) have become a basis of almost all state-of-the-art machine learning algorithms and classifiers. While NNs have been shown to generalize well to real-world examples, researchers have struggled to show why they work on an intuitive level. We designed several methods to explain the decisions of two state-of-the-art NN classifiers, ResNet and an All-CNN, in the context of the Japanese Society of Radiological Technology (JSRT) lung nodule dataset and the CIFAR-10 image dataset. Leading explanation methods LIME and Grad-CAM generate variations of heat maps which represent the regions of the input determined salient by the NN. We analyze …
Reward Modulated Spike Timing Dependent Plasticity Based Learning Mechanism In Spiking Neural Networks, Shrihari Sridharan, Gopalakrishnan Srinivasan, Kaushik Roy
Reward Modulated Spike Timing Dependent Plasticity Based Learning Mechanism In Spiking Neural Networks, Shrihari Sridharan, Gopalakrishnan Srinivasan, Kaushik Roy
The Summer Undergraduate Research Fellowship (SURF) Symposium
Spiking Neural Networks (SNNs) are one of the recent advances in machine learning that aim to further emulate the computations performed in the human brain. The efficiency of such networks stems from the fact that information is encoded as spikes, which is a paradigm shift from the computing model of the traditional neural networks. Spike Timing Dependent Plasticity (STDP), wherein the synaptic weights interconnecting the neurons are modulated based on a pair of pre- and post-synaptic spikes is widely used to achieve synaptic learning. The learning mechanism is extremely sensitive to the parameters governing the neuron dynamics, the extent of …
Model-Free Method Of Reinforcement Learning For Visual Tasks, Jeff S. Soldate, Jonghoon Jin, Eugenio Culurciello
Model-Free Method Of Reinforcement Learning For Visual Tasks, Jeff S. Soldate, Jonghoon Jin, Eugenio Culurciello
The Summer Undergraduate Research Fellowship (SURF) Symposium
There has been success in recent years for neural networks in applications requiring high level intelligence such as categorization and assessment. In this work, we present a neural network model to learn control policies using reinforcement learning. It takes a raw pixel representation of the current state and outputs an approximation of a Q value function made with a neural network that represents the expected reward for each possible state-action pair. The action is chosen an \epsilon-greedy policy, choosing the highest expected reward with a small chance of random action. We used gradient descent to update the weights and biases …