Archive for the ‘Machine Learning’ Category

Powerful new Meta AI tool can identify individual items within images – Tech Xplore

This article has been reviewed according to ScienceX's editorial process and policies. Editors have highlighted the following attributes while ensuring the content's credibility:

fact-checked

preprint

trusted source

proofread

by Peter Grad , Tech Xplore

We aim to build a foundation model for segmentation by introducing three interconnected components: a promptable segmentation task, a segmentation model (SAM) that powers data annotation and enables zero-shot transfer to a range of tasks via prompt engineering, and a data engine for collecting SA-1B, our dataset of over 1 billion masks. Credit: arXiv (2023). DOI: 10.48550/arxiv.2304.02643

Meta took a big leap forward this week with the unveiling of a model that can detect and isolate objects in an image even if it never saw them before. The technology is introduced and described in an article on the arXiv pre-print server.

The AI tool represents a major advance in one of technology's tougher challenges: allowing computers to detect and comprehend the elements of a previously unseen image and isolate them for user interaction.

It recalls a concept the former chair of the National Security Commission on Artificial Intelligence Robert O. Work once described: "What AI and machine learning allows you to do is find the needle in the haystack."

In this instance, Meta's Segment Anything Model (SAM) hunts for related pixels in an image and identifies the common components that make up all the pieces of the picture.

"SAM has learned a general notion of what objects are, and it can generate masks for any object in any image or any video, even including objects and image types that it had not encountered during training," Meta AI announced in a blog post Wednesday.

The recognition task is called segmentation. We do it daily without a moment's thought. We recognize items on our offices desks such as smartphones, cables, computer screen, a lamp, a melting candy bar, a cup of coffee.

But without prior programming, a computer must strain to distinguish all components down to the last pixel in a two-dimensional image, and it's more complicated when there are overlapping items, shadows or an irregular or partitioned shape.

Prior approaches to segmentation usually required human intervention to define a mask. Earlier automated segmentation permitted detection of objects but, according to Meta AI, that required "thousands or even tens of thousands of examples" of objects along with "computer resources and technical expertise to train the segmentation model."

SAM incorporates the two approaches in a fully automated system. It employs more than 1 billion masks that allow it to recognize new types of objects.

"This ability to generalize means that, by and large, practitioners will no longer need to collect their own segmentation data and fine-tune a model for their use case," the Meta blog stated.

One reviewer called SAM "Photoshop's 'Magic Wand' tool on steroids."

SAM can be activated by user clicks or text prompts. Meta researchers envision SAM's further utilization in the AR/VR realm. When users focus on an object, it can be delineated, defined and "lifted" into a 3D image and incorporated into a movie, game or presentation.

A free working model is available online. Users can select from an image gallery or upload their own photos. They can then tap anywhere on the screen or draw a rectangle around an item of interest and watch SAM define, for instance, the outline of a nose, face or entire body. Another option directs SAM to identify every object in an image.

Although SAM has not been applied to Facebook yet, similar technology has been applied to familiar processes such as photo tagging, moderation and tagging of disallowed content, and generation of recommended posts on both Facebook and Instagram.

2023 Science X Network

Read more from the original source:
Powerful new Meta AI tool can identify individual items within images - Tech Xplore

Using Machine Learning To Increase Yield And Lower Packaging … – SemiEngineering

Packaging is becoming more and more challenging and costly. Whether the reason is substrate shortages or the increased complexity of packages themselves, outsourced semiconductor assembly and test (OSAT) houses have to spend more money, more time and more resources on assembly and testing. As such, one of the more important challenges facing OSATs today is managing die that pass testing at the fab level but fail during the final package test.

But first, lets take a step back in the process and talk about the front-end. A semiconductor fab will produce hundreds of wafers per week, and these wafers are verified by product testing programs. The ones that pass are sent to an OSAT for packaging and final testing. Any units that fail at the final testing stage are discarded, and the money and time spent at the OSAT dicing, packaging and testing the failed units is wasted (figure 1).

Fig. 1: The process from fab to OSAT.

According to one estimate, based on the price of a 5nm wafer for a high-end smartphone, the cost of package assembly and testing is close to 30% of the total chip cost (Table 1). Given this high percentage (30%), it is considerably more cost-effective for an OSAT to only receive wafers that are predicted to pass the final package test. This ensures fewer rejects during the final package testing step, minimized costs, and more product being shipped out. Machine learning could offer manufacturers a way to accomplish this.

Table 1: Estimated breakdown of the cost of a chip for a high-end smartphone.

Using traditional methods, an engineer obtains inline metrology/wafer electrical test results for known good wafers that pass the final package test. The engineer then conducts a correlation analysis using a yield management software statistics package to determine which parameters and factors have the highest correlation to the final test yield. Using these parameters, the engineer then performs a regression fit, and a linear/non-linear model is generated. In addition, the model set forth by the yield management software is validated with new data. However, this is not a hands-off process. A periodic manual review of the model is needed.

Machine learning takes a different approach. In contrast to the previously mentioned method, which places greater emphasis on finding the model that best explains the final package test data, an approach utilizing machine learning capabilities emphasizes a models predictive ability. Due to the limited capacity of OSATs, a machine learning model trained with metrology and product testing data at the fab level and final test package data at the OSAT level creates representative results for the final package test.

With the deployment of a machine learning model predicting the final test yield of wafers at the OSAT, bad wafers will be automatically tagged at the fab in a manufacturing execution system and given an assigned wafer grade of last-to-ship (LTS). Fab real-time dispatching will move wafers with the assigned wafer grade to an LTS wafer bank, while wafers that meet the passing criteria of the machine learning model will be shipped to the OSAT, thus ensuring only good parts are sent to the packaging house for dicing and packaging. Moreover, additional production data would be used to validate the machine learning models predictions, with the end result being increased confidence in the model. A blind test can even examine specific critical parts of a wafer.

The machine learning approach also offers several advantages to more traditional approaches. This model is inherently tolerant of out-of-control conditions, trends and patterns are easily identified, the results can be improved with more data, and perhaps most significantly, no human intervention is needed.

Unfortunately, there are downsides. A large volume of data is needed for a machine learning model to make accurate predictions, but while more data is always welcome, this approach is not ideal for new products or R&D scenarios. In addition, this machine learning approach requires significant allocations of time and resources, and that means more compute power and more time to process complete datasets.

Furthermore, questions will need to be asked about the quality of the algorithm being used. Perhaps it is not the right model and, as a result, will not be able to deliver the correct results. Or perhaps the reasoning for the algorithms predictions are difficult to understand. Simply put: How does the algorithm decide which wafers are, in fact, good and which will be marked Last to Ship? And then there is the matter that incorrect or incomplete data will deliver poor results. Or as the saying goes, garbage in, garbage out.

The early detection and prediction of only good products shipping to OSATs has become increasingly critical, in part because the testing of semiconductor parts is the most expensive part of the manufacturing flow. By only testing good parts through the creation of a highly leveraged yield/operations management platform and machine learning, OSAT houses are able to increase capital utilization and return on investment, thus ensuring cost effectiveness and a continuous supply of finished goods to end customers. While this is one example of the effectiveness of machine learning models, there is so much more to learn about how such approaches can increase yield and lower costs for OSATs.

Excerpt from:
Using Machine Learning To Increase Yield And Lower Packaging ... - SemiEngineering

For chatbots and beyond: Improving lives with data starts with … – Virginia Tech Daily

ChatGPT, an AI chatbot launched this fall, allows users to ask for help with things such as writing essays, drafting business plans, generating code, and even composing music. As of Dec. 4, ChatGPT already had over 1 million users.

Open AI built its auto-generative system on a model called GPT 3, which is trained on billions of tokens. These tokens, used for natural language processing, are similar to words in a paragraph. For comparisons sake, the novel Harry Potter and the Order of the Phoenix has about 250,000 words and 185,000 tokens. Essentially, ChatGPT has been trained on billions of data points, making this kind of intelligent machine possible.

Jia noted the importance of data quality and how it can impact machine learning results.

If you have bad data feeding into machine learning, you will get bad results, said Jia. We call that 'garbage in, garbage out.' We want to get an understanding, especially a quantitative understanding, of which data is more valuable and which is less valuable for the purpose of data selection.

The importance of more quality-based data has been noticed by ChatGPT developers as they just announced the release of GPT-4. The latest technology is multimodal, meaning images as well as text prompts can spur it to generate content.

A large amount of data is required to develop this type of machine intelligence, but not all data is open sourced or public. Some data sets are owned by private entities and there is privacy involved. Jia hopes that in the future, monetary incentives can be introduced to help acquire these types of data sets and improve the machine learning algorithms that are needed in all industries.

The University of California-Berkeley grad has had conversations with Google Research and Sony AI Research, among others, who are interested in the research benefits. Jia hopes these companies will adopt the technology developed and serve as advocates for data sharing. Sharing data and adopting improved machine learning algorithms will greatly benefit not only industries but individual consumers as well. For instance, if youve ever had a bad experience with a customer service chatbot, youve experienced low-quality data and poor machine learning algorithm design.

Jia hopes to use her background and area expertise to improve these web-based interactions for all. As a school-aged child, Jia always enjoyed math and science, but her decision to enter the electrical and computer engineering field stemmed from her desire to help people.

Both of my parents are doctors. It was amazing to grow up seeing them help patients with some kind of medical formula, said Jia. Thats why I chose to study math and science. You can have a concrete impact. Im using a different kind of formula to help, but I like that pursuing this career has made me feel like I can make a difference in someones life.

The CAREER award is the National Science Foundations most prestigious award for early-career faculty with the potential to serve as academic role models in research and education and to lead advances in their organizations mission. Throughout this project, Jia has demonstrated her desire to serve as an academic role model for graduate, undergraduate, and even K-12 students.

She is a core faculty in theSanghani Center for Artificial Intelligence and Data Analytics, formerly known as the Discovery Analytics Center. The center has more than 20 faculty members and 120 graduate students, two of whom are working directly with Jia to conduct the planned research.

See the original post:
For chatbots and beyond: Improving lives with data starts with ... - Virginia Tech Daily

Machine learning based prediction for oncologic outcomes of renal … – Nature.com

Using the original KORCC database9, two recent studies have been reported28,29. At first, Byun et al.28 assessed the prognosis of non-metastatic clear cell RCC using a deep learning-based survival predictions model. Harrels C-indices of DeepSurv for recurrence and cancer-specific survival were 0.802 and 0.834, respectively. More recently, Kim et al.29 developed ML-based algorithm predicting the probability of recurrence at 5 and 10years after surgery. The highest area under the receiver operating characteristic curve (AUROC) was obtained from the nave Bayes (NB) model, with values of 0.836 and 0.784 at 5 and 10years, respectively.

In the current study, we used the updated KORCC database. It now contains clinical data of more than 10,000 patients. To the best of our knowledge, this is the largest dataset in Asian population with RCC. With this dataset, we could develop much more accurate models with very high accuracy (range, 0.770.94) and F1-score (range, 0.770.97, Table 3). The accuracy values were relatively high compared to the previous models, including the Kattan nomogram, Leibovich model, the GRANT score, which were around 0.75,6,7,8. Among them, the Kattan nomogram was developed using a cohort of 601 patients with clinically localized RCC, and the overall C-index was 74%5. In a subsequent analysis with the same patient group using an additional prognostic variables including tumor necrosis, vascular invasion, and tumor grade, the C-index was as high as 82%30. Their prediction accuracies were not as high as ours yet.

In addition, we could include short-term (3-year) recurrence and survival data, which would be helpful for developing more sophisticated surveillance strategy. The other strength of current study was that most algorithms introduced so far had been applied18,19,20,21,22,23,24,25,26, showing relatively consistent performance with high accuracy. Finally, we also performed an external validation by using a separate (SNUBH) cohort, and achieved well maintained high accuracy and F1-score in both recurrence and survival (Fig.2). External validation of prediction models is essential, especially in case of using the multi-institutional dataset, to ensure and correct for differences between institutions.

AUROC has been mostly used as the standard evaluating performance of prediction models5,6,7,8,29. However, AUROC weighs changes in sensitivity and specificity equally without considering clinically meaningful information6. In addition, the lack of ability to compare performance of different ML models is another limitation of AUROC technique31. Thus, we adopted accuracy and F1-score instead of AUROC as evaluation metrics. F1-score, in addition to SMOTE17, is used as better accuracy metrics to solve the imbalanced data problems27.

RCC is not a single disease, but multiple histologically defined cancers with different genetic characteristics, clinical courses, and therapeutic responses32. With regard to metastatic RCC, the International Metastatic Renal Cell Carcinoma Database Consortium and the Memorial Sloan Kettering Cancer Center risk model have been extensively validated and widely used to predict survival outcomes of patients receiving systemic therapy33,34. However, both risk models had been developed without considering histologic subtypes. Thus, the predictive performance was presumed to have been strongly affected by clear cell type (predominant histologic subtype) RCC. Interestingly, in our previous study using the Korean metastatic RCC registry, we found the both risk models reliably predicted progression and survival even in non-clear cell type RCC35. In the current study, after performing subgroup analysis according to the histologic type (clear vs. non-clear cell type RCC), we also found very high accuracy and F1-score in all tested metrics (Supplemental Tables 3 and 4). Taking together, these findings suggest that the prognostic difference between clear and non-clear cell type RCC seems to be offset both in metastatic and non-metastatic RCC. Further effort is needed to develop and validate a sophisticated prediction model for individual subtypes of non-clear cell type RCC.

The current study had several limitations. First, due to the paucity of long-term follow-up cases at 10years, data imbalance problem could not be avoided. Subsequently, recurrence-free rate at 10-year was reported only to be 45.3%. In the majority of patients, further long-term follow up had not been performed in case of no evidence of disease at five years. However, we adopted both SMOTE and F1-score to solve these imbalanced data problems. The retrospective design of this study was also an inherent limitation. Another limitation was that the developed prediction model only included the Korean population. Validation of the model using data from other countries and races is also needed. In regard of non-clear cell type RCC, the current study cohort is still relatively small due to the rarity of the disease, we could not avoid integrating each subtype and analyzing together. Thus, further studies is still needed to develop and validate a prediction model for each subtypes. In addition, the lack of more accurate classifiers such as cross-validation and bootstrapping is another limitation of current study. Finally, the web-embedded deployment of model should be followed to improve accessibility and transportability.

Originally posted here:
Machine learning based prediction for oncologic outcomes of renal ... - Nature.com

Students Use Machine Learning in Lesson Designed to Reveal … – NC State News

In a new study, North Carolina State University researchers had 28 high school students create their own machine-learning artificial intelligence (AI) models for analyzing data. The goals of the project were to help students explore the challenges, limitations and promise of AI, and to ensure a future workforce is prepared to make use of AI tools.

The study was conducted in conjunction with a high school journalism class in the Northeast. Since then, researchers have expanded the program to high school classrooms in multiple states, including North Carolina. NCState researchers are looking to partner with additional schools to collaborate in bringing the curriculum into classrooms.

We want students, from a very young age, to open up that black box so they arent afraid of AI, said the studys lead author Shiyan Jiang, assistant professor of learning design and technology at NCState. We want students to know the potential and challenges of AI, and so they think about how they, the next generation, can respond to the evolving role of AI and society. We want to prepare students for the future workforce.

For the study, researchers developed a computer program called StoryQ that allows students to build their own machine-learning models. Then, researchers hosted a teacher workshop about the machine learning curriculum and technology in one-and-a-half hour sessions each week for a month. For teachers who signed up to participate further, researchers did another recap of the curriculum for participating teachers, and worked out logistics.

We created the StoryQ technology to allow students in high school or undergraduate classrooms to build what we call text classification models, Jiang said. We wanted to lower the barriers so students can really know whats going on in machine-learning, instead of struggling with the coding. So we created StoryQ, a tool that allows students to understand the nuances in building machine-learning and text classification models.

A teacher who decided to participate led a journalism class through a 15-day lesson where they used StoryQ to evaluate a series of Yelp reviews about ice cream stores. Students developed models to predict if reviews were positive or negative based on the language.

The teacher saw the relevance of the program to journalism, Jiang said. This was a very diverse class with many students who are under-represented in STEM and in computing. Overall, we found students enjoyed the lessons a lot, and had great discussions about the use and mechanism of machine-learning.

Researchers saw that students made hypotheses about specific words in the Yelp reviews, which they thought would predict if a review would be positive, or negative. For example, they expected reviews containing the word like to be positive. Then, the teacher guided the students to analyze whether their models correctly classified reviews. For example, a student who used the word like to predict reviews found that more than half of reviews containing the word were actually negative. Then, researchers said students used trial and error to try to improve the accuracy of their models.

Students learned how these models make decisions, and the role that humans can play in creating these technologies, and the kind of perspectives that can be brought in when they create AI technology, Jiang said.

From their discussions, researchers found that students had mixed reactions to AI technologies. Students were deeply concerned, for example, about the potential to use AI to automate processes for selecting students or candidates for opportunities like scholarships or programs.

For future classes, researchers created a shorter, five-hour program. Theyve launched the program in two high schools in North Carolina, as well as schools in Georgia, Maryland and Massachusetts. In the next phase of their research, they are looking to study how teachers across disciplines collaborate to launch an AI-focused program and create a community of AI learning.

We want to expand the implementation in North Carolina, Jiang said. If there are any schools interested, we are always ready to bring this program to a school. Since we know teachers are super busy, were offering a shorter professional development course, and we also provide a stipend for teachers. We will go into the classroom to teach if needed, or demonstrate how we would teach the curriculum so teachers can replicate, adapt, and revise it. We will support teachers in all the ways we can.

The study, High school students data modeling practices and processes: From modeling unstructured data to evaluating automated decisions, was published online March 13 in the journal Learning, Media and Technology. Co-authors included Hengtao Tang, Cansu Tatar, Carolyn P. Ros and Jie Chao. The work was supported by the National Science Foundation under grant number 1949110.

-oleniacz-

Note to Editors: The study abstract follows.

High school students data modeling practices and processes: From modeling unstructured data to evaluating automated decisions

Authors: Shiyan Jiang, Hengtao Tang, Cansu Tatar, Carolyn P. Ros and Jie Chao.

Published: March 13, 2023, Learning, Media and Technology

DOI: 10.1080/17439884.2023.2189735

Abstract: Its critical to foster artificial intelligence (AI) literacy for high school students, the first generation to grow up surrounded by AI, to understand working mechanism of data-driven AI technologies and critically evaluate automated decisions from predictive models. While efforts have been made to engage youth in understanding AI through developing machine learning models, few provided in-depth insights into the nuanced learning processes. In this study, we examined high school students data modeling practices and processes. Twenty-eight students developed machine learning models with text data for classifying negative and positive reviews of ice cream stores. We identified nine data modeling practices that describe students processes of model exploration, development, and testing and two themes about evaluating automated decisions from data technologies. The results provide implications for designing accessible data modeling experiences for students to understand data justice as well as the role and responsibility of data modelers in creating AI technologies.

Read more here:
Students Use Machine Learning in Lesson Designed to Reveal ... - NC State News