AI Tools for Projects:
- Otter AI: You can take voice notes as you progress through your project.
2. Goblin Tools
3. Padlet
| Introduction to Programming (Python)Basic Ai Concepts – Machine LearningUnderstanding Algorithms “Machine Learning/AI Toolbox: Python Python is my preferred programming language for AI/ML because of its simplicity, readability, and extensive libraries. It provides a beginner-friendly environment, ideal for learning and implementing machine learning concepts. There is a learning curve, as with any programming language, but I find it’s easier to get going quickly. I’ll list some of the key libraries below. Managing libraries and environments in Python can be a bit of a pain, but distributions such as Anaconda can help make this a bit easier. Data Processing Libraries Jupyter Notebooks Jupyter is an interactive notebook where students can write code, run it, and immediately see the output, all in one place. It’s widely used for data science and machine learning because it allows combining code, comments, and visualizations, which is very helpful for understanding how different steps in AI work. We often use Jupyter for client work as it’s easy to format data analytics projects into nicely formatted documents. NumPy A library for working with large, multi-dimensional arrays and matrices, along with a vast collection of mathematical functions. Essential for handling data in machine learning. Pandas Built on top of NumPy, it provides data structures like DataFrames, which make data manipulation and analysis easier. It’s crucial for preprocessing and organising datasets, making it easier to handle data. Matplotlib A library for creating visualizations in Python. It’s commonly used for plotting data, which is useful for understanding data trends and evaluating model results. Users can create graphs, charts, and plots to see their data or model’s performance visually. The formatting options are fairly limited but libraries such as Seaborn can help things look a bit nicer. Machine Learning/AI Scikit-Learn One of the most popular machine learning libraries in Python, scikit-learn provides tools for training, testing, and evaluating machine learning models. It has pre-built algorithms for classification, regression, clustering, and more, making it easy for beginners to experiment with AI. OpenCV OpenCV is a library focused on computer vision, which includes tasks like image and video processing. This is especially interesting for projects involving image recognition, face detection, or any kind of visual data processing. TensorFlow A deep learning library developed by Google. It’s more complex but provides a lot of flexibility for designing neural networks and advanced models. TensorFlow Lite also allows experimenting with ML on mobile devices. This might be on the more advanced end of the spectrum. PyTorch Similar to TensorFlow but developed by Facebook and a bit more beginner-friendly and is popular in research and education. Both libraries are good for experimenting with neural networks. Keras An API designed for building and training deep learning models. It often works with TensorFlow as a backend and provides a simpler, high-level way to create complex neural networks, making it easier for beginners to get into deep learning. NLTK Natural Language Toolkit, used for working with human language data (text). It provides tools for tokenizing, parsing, and analyzing text, great for language-based projects. spaCy A more advanced NLP library that’s efficient and suitable for building applications involving language processing. It’s simpler and faster than NLTK for larger projects. List provided by Patrick Murray |
Recent Comments