Machine Learning/AI:


Developing algorithms to enable digital systems to automatically learn and improve their performance over time.


Roadmap

  • Goals

  • Introduction: AI/Neural Networks/Machine Larning

  • Deep dive: Applied ML/AI in neuroscience

Introduction to Natural Language Processing

Natural Language Processing (NLP) is a field of computer science and artificial intelligence that focuses on developing systems that can understand and generate human language. This field has applications in areas such as chatbots, speech recognition, and sentiment analysis, and has the potential to revolutionize the way we interact with technology.

NLP involves using computer algorithms to analyze and understand human language, including its structure, meaning, and context. This allows computers to process and respond to natural language inputs, such as spoken or written text, in a way that is similar to how humans process language.

The goal of NLP is to enable computers to understand and generate human language in a way that is both accurate and natural. This is a challenging task, as human language is complex and nuanced, and can be difficult for computers to interpret. However, advances in NLP have led to the development of systems that are capable of performing complex language-related tasks, such as answering questions, translating between languages, and even writing creative text.

As a student of NLP, you will learn about the theories a

Artifical Intelligence (AI)

Artificial Intelligence (AI) is a branch of computer science that deals with the creation of intelligent machines that work and react like humans. The goal of AI is to develop systems that can perform tasks that typically require human intelligence, such as speech recognition, decision making, and problem solving.

In scientific research, AI has become an increasingly important tool for analyzing large amounts of data and making predictions and discoveries in a variety of fields, including biology, medicine, physics, and astronomy. AI algorithms can help scientists find patterns and relationships in data that would be difficult or impossible for humans to detect, leading to new insights and breakthroughs.


The benefits of AI for scientific research include increased accuracy, efficiency, and the ability to handle large amounts of data. Additionally, AI can automate tedious and time-consuming tasks, freeing up scientists to focus on more high-level tasks. AI can also help make new discoveries and predictions that would not have been possible without it, leading to a better understanding of the world and faster progress in various fields.


Strong vs. Weak Intelligence

Jonathan L Reyes
@jlrreyes

Not every AI is created equal. Generally, we differentiate two main types of AI: weak AI and strong AI.

Weak AI (also known as narrow AI) is designed to only perform specific tasks of a limited scope. For example, a chatbot that helps customers with simple inquiries or a voice assistant that plays music on command. Weak AI is programmed to respond to specific inputs in a predefined manner, but it does not possess the ability to learn or reason beyond its programmed instructions.

A strong AI, however, (also known as general AI or artificial general intelligence (AGI)) is designed to have human-like cognitive abilities such as reasoning, learning, and problem-solving. Strong AI is capable of performing a wide range of tasks, including those that it has not been specifically programmed for. In other words, it has the ability to learn and adapt on its own.

While weak AI is currently the most prevalent form of AI, many experts believe that strong AI has the potential to impact our society significantly in the future. It could revolutionize fields such as healthcare, finance, and transportation by providing more accurate and efficient decision-making.


Neural Networks

The term neural network is often brought up once conversations about AI started. But what are neural networks?

Illustration of a simple neural network

Neural networks are a type of machine learning algorithm modeled after the structure and function of the human brain. They are designed to recognize complex patterns and relationships in data and to use that information to make predictions or decisions.

At their core, neural networks consist of layers of interconnected nodes called neurons, which are responsible for processing and transmitting information. Each neuron takes input data, applies a mathematical transformation to that data, and then passes the transformed data on to the next layer of neurons. This process continues until the final layer of neurons produces the network’s output.

This really is only the most basic description. Further down the line, we will go into more detail. However, we highly recommend 3Blue1Brown’s introduction on what Neural Networks are for a more in-depth look into the topic!


Machine Learning

Machine learning is a subfield of artificial intelligence (AI) that involves the development of algorithms that can learn from and make predictions or decisions based on data. The goal of machine learning is to allow computers to recognize patterns, make predictions, or classify data.

The purpose of machine learning is to provide computers with the ability to automatically improve their performance on a given task by learning from experience without being explicitly programmed to perform that task. This allows machines to make better decisions or predictions as they are exposed to more data and improve over time.

Machine learning is different from classical statistics in that it focuses on the development of algorithms that can learn from data and make predictions, whereas classical statistics focuses on the use of statistical models to make inferences and predictions based on data. Additionally, classical statistics requires a priori knowledge of the relationships between variables and the distribution of data, whereas machine learning algorithms can discover these relationships and distributions on their own through training.

Illustration of the differences of AI, Deep Learning and Machine Learning

Deep dive: Applied ML/AI in Neuroscience

In the following sub-chapters, we will do a deep dive into the specifics of ML/AI, how to use them via Python, and how these techniques may be utilized for neuroscience!