- ScholarSphere Newsletter
- Posts
- ScholarSphere Newsletter #13
ScholarSphere Newsletter #13
Where AI meets Academia
Welcome to 13th edition of ScholarSphere
“Happiness shared is happiness doubled ”
Welcome to our AI Newsletter—your ultimate guide to the rapidly changing world of AI in academia. If you haven't joined us yet, now's your chance! Click that button, subscribe with your email, and get ready for an exciting journey through all things AI in the academic realm!
In today's search of AI, we'll see...
Deep Dive into AI: Expand Your Knowledge
AI in Cryptocurrency Investing
By Nicole Willing, Techopedia
What Makes AI Useful?
Traditional market analysis is time-consuming. AI can analyze large datasets to identify profitable investment opportunities and make predictions. AI tools can also monitor markets in real-time and provide alerts to potential market changes.
4 Use Cases of AI
Data Analysis: Gain insights into market dynamics and identify patterns.
Real-time Market Monitoring: Continuously track price fluctuations and other market drivers.
Risk Assessment: Assess the risk levels associated with different cryptocurrencies.
Automation: Automate the process of buying and selling cryptocurrencies.
Types of AI Trading Tools
Trading Bots: These can be automated or implement dollar-cost averaging for long-term investment.
Social Media Integration: Analyze sentiment from social media platforms to determine market sentiment.
eToro offers an AI-based feature that brings in relevant tweets and allows users to trade within Twitter.
Price Forecasting: Analyze data to predict future price trends.
Machine learning allows users to create algorithms for price predictions.
Risk Management: Assess the risk of investing in various cryptocurrencies.
Coinbase is testing ChatGPT to assist its risk analysis.
AI tools can construct cryptocurrency portfolios based on pricing and risk analysis.
How AI-Powered Trading Automation Works
AI algorithms can be trained on historical data to make predictions and execute trades.
Machine learning: Trains an algorithm to make predictions about future data.
Deep learning: Uses multi-layered neural networks to learn and make predictions from data.
Reinforcement learning: Trains AI algorithms to make decisions through a system of rewards and penalties.
How AI Sentiment Analysis Works
AI can analyze large volumes of data from various sources to determine market sentiment.
Natural language processing is used to identify whether the content is positive or negative.
Based on the data analysis, the algorithm can provide traders with a sentiment score.
Examples of AI-Based Cryptocurrency Trading Tools
SingularityNET: A decentralized network that allows users to create and monetize AI-based services.
TensorCharts: Provides live market data visualization using AI.
Cryptoindex: Provides AI-based analytical tools.
Kryll.io: Allows users to create or rent AI bots to automate their trading.
HypeIndex: Analyzes sentiment on cryptocurrencies and stocks.
3 Tips For Using AI Tools
Verify information before finalizing trades.
Do your own research in addition to using AI tools.
Be aware of security risks associated with AI tools.
The Bottom Line
AI can be a valuable tool for cryptocurrency traders and investors. It can analyze data, forecast market movements, and detect potential risks. However, AI should be used in conjunction with other forms of analysis and should not be your only source of research.
For reading the full article click here.
You can also find extra teaching articles in our LinkedIn Page.
Mastering AI: Prompt Perfection
Automatic Chain of Thought (Auto_CoT) & Self-Consistency
By aman.ai
Automatic Chain of Thought (Auto_CoT)
When applying Chain-of-Thought prompting with demonstrations, the process involves hand-crafting effective and diverse examples. This manual effort could lead to suboptimal solutions. Zhang, et al. (2022) propose an approach to eliminate manual efforts by leveraging LLMs with “Let’s think step by step” prompt to generate reasoning chains for demonstrations one by one. This automatic process can still end up with mistakes in generated chains. To mitigate the effects of the mistakes, the diversity of demonstrations matter. This works proposes Auto-CoT, which samples questions with diversity and generates reasoning chains to construct the demonstrations.
Auto-CoT consists of two main stages:
Stage 1: Question Clustering: partition questions of a given dataset into a few clusters
Stage 2: Demonstration Sampling: select a representative question from each cluster and generate its reasoning chain using Zero-Shot-CoT with simple heuristics
The simple heuristics could be length of questions (e.g., 60 tokens) and number of steps in rationale (e.g., 5 reasoning steps). This encourages the model to use simple and accurate demonstrations.
The process is illustrated below (source):
Code for Auto-CoT is available here.
Self-Consistency
Perhaps one of the more advanced techniques out there for prompt engineering is self-consistency. Proposed by Wang, et al. (2022), self-consistency aims “to replace the naive greedy decoding used in chain-of-thought prompting”. The idea is to sample multiple, diverse reasoning paths through few-shot CoT, and use the generations to select the most consistent answer. This helps to boost the performance of CoT prompting on tasks involving arithmetic and commonsense reasoning.
Computing for the final answer involves a few steps (check out the paper for the details) but for the sake of simplicity, we can see that there is already a majority answer emerging so that would essentially become the final answer.
Full getting access to our Prompt Inventory check here
Don’t forget to visit our LinkedIn Page
Cutting-Edge AI Insights for Academia
UniversityWorldNews: Half of HE institutions use AI in teaching – Survey
AcademicApproach: The AI Revolution in Education: Challenges and Opportunities
Polish artist Agnieszka Pilat poses with the artwork of her robot painting dogs - Basia Spot and Bunny Spot - who have become artists painting on canvases with their paws, at the launch of the National Gallery of Victoria (NGV) Triennial 2023 in Melbourne on April 5, 2023. - Pilat works with the Boston Dynamics dogs, training them to paint autonomously through AI technology individually and collaboratively, and will be part of more than 100 local and international artists, designers and collectives presenting at the exhibition opening in December. (Photo by William WEST / AFP) / RESTRICTED TO EDITORIAL USE
Image created with Adobe Firefly
Article of the Week: Williamson, B. The Social life of AI in Education. Int J Artif Intell Educ 34, 97–104 (2024). https://doi.org/10.1007/s40593-023-00342-5
Spotlight on AI Tools for Academic Excellence
10Web: The first AI-Powered WordPress Platform that simplifies and accelerates the entire website building, hosting, speed and management process, meeting the needs of website building for beginners.
Humata: Chat your way through long documents. Command our PDF AI to summarize for you.
Cognito: an intelligent learning platform that uses videos, questions and past papers to help you best prepare for exams. Content is specific to your course and covers all of GCSE Science and Maths.
Mykin: A personal AI for your private life. Get inspired, talk things through, navigate situations or get personalized guidance with Kin. Built for privacy, security, and with memory in mind.
Socratic: A learning platform that helps students get unstuck and learn better by providing answers, math solvers, explanations, and videos for homework questions in various subjects such as Math, Science, History, English, and more.
Reply