Filtering by
- All Subjects: Machine Learning
- Creators: Computer Science and Engineering Program
![147844-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-07/147844-Thumbnail%20Image.png?versionId=B_MMhDbedPR_rFOTMQxIiyRykWmTIQJu&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240530/us-west-2/s3/aws4_request&X-Amz-Date=20240530T171214Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=74aff55c3a7217696f59447f5eceb1d726ed0e03296d22fb328d84e8f20ab0a7&itok=vN_-2TmP)
"No civil discourse, no cooperation; misinformation, mistruth." These were the words of former Facebook Vice President Chamath Palihapitiya who publicly expressed his regret in a 2017 interview over his role in co-creating Facebook. Palihapitiya shared that social media is ripping apart the social fabric of society and he also sounded the alarm regarding social media’s unavoidable global impact. He is only one of social media’s countless critics. The more disturbing issue resides in the empirical evidence supporting such notions. At least 95% of adolescents own a smartphone and spend an average time of two to four hours a day on social media. Moreover, 91% of 16-24-year-olds use social media, yet youth rate Instagram, Facebook, and Twitter as the worst social media platforms. However, the social, clinical, and neurodevelopment ramifications of using social media regularly are only beginning to emerge in research. Early research findings show that social media platforms trigger anxiety, depression, low self-esteem, and other negative mental health effects. These negative mental health symptoms are commonly reported by individuals from of 18-25-years old, a unique period of human development known as emerging adulthood. Although emerging adulthood is characterized by identity exploration, unbounded optimism, and freedom from most responsibilities, it also serves as a high-risk period for the onset of most psychological disorders. Despite social media’s adverse impacts, it retains its utility as it facilitates identity exploration and virtual socialization for emerging adults. Investigating the “user-centered” design and neuroscience underlying social media platforms can help reveal, and potentially mitigate, the onset of negative mental health consequences among emerging adults. Effectively deconstructing the Facebook, Twitter, and Instagram (i.e., hereafter referred to as “The Big Three”) will require an extensive analysis into common features across platforms. A few examples of these design features include: like and reaction counters, perpetual news feeds, and omnipresent banners and notifications surrounding the user’s viewport. Such social media features are inherently designed to stimulate specific neurotransmitters and hormones such as dopamine, serotonin, and cortisol. Identifying such predacious social media features that unknowingly manipulate and highjack emerging adults’ brain chemistry will serve as a first step in mitigating the negative mental health effects of today’s social media platforms. A second concrete step will involve altering or eliminating said features by creating a social media platform that supports and even enhances mental well-being.
Robots are often used in long-duration scenarios, such as on the surface of Mars,where they may need to adapt to environmental changes. Typically, robots have been built specifically for single tasks, such as moving boxes in a warehouse or surveying construction sites. However, there is a modern trend away from human hand-engineering and toward robot learning. To this end, the ideal robot is not engineered,but automatically designed for a specific task. This thesis focuses on robots which learn path-planning algorithms for specific environments. Learning is accomplished via genetic programming. Path-planners are represented as Python code, which is optimized via Pareto evolution. These planners are encouraged to explore curiously and efficiently. This research asks the questions: “How can robots exhibit life-long learning where they adapt to changing environments in a robust way?”, and “How can robots learn to be curious?”.
![136409-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-05/136409-Thumbnail%20Image.png?versionId=XcLyIrVJ.o_SJLsDP7bBteXGsQ08gph0&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240617/us-west-2/s3/aws4_request&X-Amz-Date=20240617T235537Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=987fa7bb5004071f2449f35e57dde0d1f9775a1d881fe2b1ac174629036fcdfe&itok=MvHc7kOa)
![136516-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-05/136516-Thumbnail%20Image.png?versionId=zdxRLbqfCc8UpbvipICAN8JSwisowPcO&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240612/us-west-2/s3/aws4_request&X-Amz-Date=20240612T030913Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=c80ef2e7080fdaed4a0c566882c620039eac32d23e223dd72196ba82e0ae071d&itok=CEvw5jV9)
![135758-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-05/135758-Thumbnail%20Image.png?versionId=m6hhqvtqZnRbVaRPMs4its6fq1gAiLAN&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240618/us-west-2/s3/aws4_request&X-Amz-Date=20240618T023748Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=3507ce7afd1ad8a6467dd7f01647265377d4198bc94c54fa613b1a7725e714c3&itok=BOaHtyww)
![137156-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-05/137156-Thumbnail%20Image.png?versionId=QrNB2WkCCIZHp3xpBS8.LSOPtaWsOu5V&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240618/us-west-2/s3/aws4_request&X-Amz-Date=20240618T165022Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=1cea02f6a8c26cb4286883913ba0f05165075c3f9a15725a2084a446249ec276&itok=xycsJ2rB)
![136386-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-05/136386-Thumbnail%20Image.png?versionId=ffDedcAyGKm7TmZf4q_mHqY_GtK9bP1R&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240618/us-west-2/s3/aws4_request&X-Amz-Date=20240618T130251Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=02ced47b119029077104e53dceed5bf460ae67179a5c0fd1be92f5db18ff5191&itok=YUov0L8S)
![147700-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-07/147700-Thumbnail%20Image.png?versionId=h4I6_GEWiZktsqJNiq9fnYG6h1y1wDt.&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240618/us-west-2/s3/aws4_request&X-Amz-Date=20240618T193015Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=b1597ea9fdb5e600380d8ccbe7dd6197f6d06857a1ad00c66afc5ac3a14c4c8f&itok=hb4RJml-)
In this paper, I introduce the fake news problem and detail how it has been exacerbated<br/>through social media. I explore current practices for fake news detection using natural language<br/>processing and current benchmarks in ranking the efficacy of various language models. Using a<br/>Twitter-specific benchmark, I attempt to reproduce the scores of six language models<br/>demonstrating their effectiveness in seven tweet classification tasks. I explain the successes and<br/>challenges in reproducing these results and provide analysis for the future implications of fake<br/>news research.
Human activity recognition is the task of identifying a person’s movement from sensors in a wearable device, such as a smartphone, smartwatch, or a medical-grade device. A great method for this task is machine learning, which is the study of algorithms that learn and improve on their own with the help of massive amounts of useful data. These classification models can accurately classify activities with the time-series data from accelerometers and gyroscopes. A significant way to improve the accuracy of these machine learning models is preprocessing the data, essentially augmenting data to make the identification of each activity, or class, easier for the model. <br/>On this topic, this paper explains the design of SigNorm, a new web application which lets users conveniently transform time-series data and view the effects of those transformations in a code-free, browser-based user interface. The second and final section explains my take on a human activity recognition problem, which involves comparing a preprocessed dataset to an un-augmented one, and comparing the differences in accuracy using a one-dimensional convolutional neural network to make classifications.
![147904-Thumbnail Image.png](https://d1rbsgppyrdqq4.cloudfront.net/s3fs-public/styles/width_400/public/2021-07/147904-Thumbnail%20Image.png?versionId=TZ44zoWNMSw_mulPyLHoeYTJarPEPaeT&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIASBVQ3ZQ42ZLA5CUJ/20240618/us-west-2/s3/aws4_request&X-Amz-Date=20240618T182347Z&X-Amz-SignedHeaders=host&X-Amz-Expires=120&X-Amz-Signature=05f12980fbefd1e39c1d115c2ee47eb898249b218ade6e965a94fb549490253f&itok=O7rSGkoj)
This paper is centered on the use of generative adversarial networks (GANs) to convert or generate RGB images from grayscale ones. The primary goal is to create sensible and colorful versions of a set of grayscale images by training a discriminator to recognize failed or generated images and training a generator to attempt to satisfy the discriminator. The network design is described in further detail below; however there are several potential issues that arise including the averaging of a color for certain images such that small details in an image are not assigned unique colors leading to a neutral blend. We attempt to mitigate this issue as much as possible.