> Markdown version of [/videos/260-getting-started-with-machine-learning](https://www.wearedevelopers.com/videos/260-getting-started-with-machine-learning). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Getting Started with Machine Learning

Want to build your first machine learning pipeline? Watch a predictive Scikit-Learn model trained live, taking you from basic statistical functions to complex deep learning architectures.

- **Speakers:** Alexandra Waldherr
- **Event:** WeAreDevelopers LIVE
- **Published:** October 6, 2021
- **Duration:** 44:11
- **URL:** https://www.wearedevelopers.com/videos/260-getting-started-with-machine-learning

## Summary

The presentation provides an accessible introduction to machine learning, tracing its evolution from early biological models of brain cells to modern deep learning architectures. It distinguishes core concepts like artificial intelligence, machine learning, and deep learning, while explaining essential statistical approaches such as linear models, decision trees, regression, and classification. The talk bridges theoretical understanding with practical application by demonstrating a complete machine learning pipeline: preparing a dataset, training a random forest model using Scikit-Learn to predict automotive CO2 emissions, and evaluating model accuracy.

Over the course of the session, the discussion dives deeper into complex topics like supervised versus unsupervised learning, reinforcement learning, and convolutional neural networks used for image recognition. A live demonstration applying the fast.ai framework on PyTorch highlights the specific impact of noisy data on image classification models, addressing common developer pitfalls such as overfitting, underfitting, and inherent data bias. This practical walkthrough emphasizes why finding the optimal learning rate and recognizing prediction errors through tools like confusion matrices are crucial for refining model accuracy.

The presentation proceeds to explore the broader industry implications of machine learning. It connects ML to the automotive sector through prominent use cases like image segmentation for autonomous driving and predictive maintenance, while also recognizing groundbreaking applications in chemistry, such as Google's AlphaFold and TensorFlow Quantum. A concluding Q&A session unpacks overarching industry concerns, emphasizing that building diverse datasets is significantly more crucial than simply collecting massive volumes of data, and highlighting the ongoing necessity for explainable AI to ensure data-driven decision-making remains safe, secure, and ethical.

**Keywords:** machine learning pipelines, deep learning architectures, scikit-learn random forest, supervised and unsupervised learning, automotive predictive maintenance, convolutional neural networks, fast.ai image classification, model overfitting scenarios, pytorch deep learning, tensorflow predictive modeling, autonomous driving image segmentation, training data bias, explainable ai methodologies, alphafold protein prediction, dataset normalization, reinforcement learning applications

## Chapters

1. **Modeling brain cells to understand artificial intelligence capabilities** (00:02) — Early artificial intelligence research focused on modeling biological brain cells to understand logic and computation.
1. **Evolution of machine learning algorithms and computing hardware** (01:59) — Breakthroughs like backpropagation and the shift from CPUs to graphical processing units accelerated machine learning capabilities.
1. **Distinguishing artificial intelligence from deep learning and statistics** (03:57) — Deep learning configures brain-like structures while machine learning leverages statistics to find patterns in data.
1. **Training a regression model to predict automotive emissions** (05:50) — Preparing a dataset with Pandas to train a random forest regressor builds predictive capabilities for emissions.
1. **Inspecting decision trees and identifying feature importance variables** (11:32) — Analyzing the underlying questions within a random forest tree reveals the most impactful predictive data features.
1. **Supervised, unsupervised, and reinforcement learning paradigms explained** (12:37) — Training methodologies range from labeled input supervision to environmental feedback loops and computational weight optimization.
1. **Structural advantages of deep neural networks and residual layers** (14:22) — Deep neural networks leverage activation functions and residual layers to process nonlinear real-world complexities effectively.
1. **Mitigating overfitting and underfitting in model training data** (15:27) — Balancing model complexity with dataset size prevents learning anomalies that cause inaccurate real-world predictions.
1. **Building image classification networks using noisy diagnostic datasets** (16:36) — Evaluating imperfect graphical data through convolutional frameworks hones classification limits and tuning rates.
1. **Architecture of convolutional and recurrent neural network structures** (21:07) — Convolutional layers isolate image shapes while recurrency and transformers track sequential context in language processing.
1. **Industrial applications of machine learning in autonomous vehicles** (22:44) — Deep learning algorithms process radar and visual data to classify objects for autonomous automotive decisions.
1. **Advancing biocatalyst research through quantum machine learning algorithms** (24:51) — Machine learning optimization of quantum circuits unlocks protein folding discoveries inside biological neural firing processes.
1. **Navigating data privacy boundaries and adversarial model reliability** (27:05) — Exploring edge cases and privacy regulations shapes the secure rollout of trustworthy predictive artificial intelligence tools.

## Related Moments

- [Introduction to safety-critical machine learning in automotive contexts](https://www.wearedevelopers.com/videos/397-what-non-automotive-machine-learning-projects-can-learn-from-automotive-machine-learning-projects) (from "What non-automotive Machine Learning projects can learn from automotive Machine Learning projects")
- [Addressing participant questions on liability and machine learning](https://www.wearedevelopers.com/videos/374-the-future-of-automotive-mobility-upcoming-e-e-architectures-v2x-and-its-challenges) (from "The future of automotive mobility: Upcoming E/E architectures, V2X and its challenges")
- [Audience questions on practical machine learning operational strategies](https://www.wearedevelopers.com/videos/262-is-my-ai-alive-but-brain-dead-how-monitoring-can-tell-you-if-your-machine-learning-stack-is-still-performing) (from "Is my AI alive but brain-dead? How monitoring can tell you if your machine learning stack is still performing")
- [Audience Q&A on autonomous driving models and data](https://www.wearedevelopers.com/videos/519-finding-the-unknown-unknowns-intelligent-data-collection-for-autonomous-driving-development) (from "Finding the unknown unknowns: intelligent data collection for autonomous driving development")
- [Familiarizing with machine learning and neural network basics](https://www.wearedevelopers.com/videos/227-uncertainty-estimation-of-neural-networks) (from "Uncertainty Estimation of Neural Networks")
- [Distinguishing between AI, machine learning, and deep learning](https://www.wearedevelopers.com/videos/844-enter-the-brave-new-world-of-genai-with-vector-search) (from "Enter the Brave New World of GenAI with Vector Search")

## Related Articles

- [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development)
- [MLOps – What’s the deal behind it?](https://www.wearedevelopers.com/magazine/125-mlops-what-s-the-deal-behind-it)
- [MLops – Deploying, Maintaining And Evolving Machine Learning Models in Production](https://www.wearedevelopers.com/magazine/115-mlops-deploying-maintaining-and-evolving-machine-learning-models-in-production)
- [Stephan Gillich - Bringing AI Everywhere](https://www.wearedevelopers.com/magazine/489-stephan-gillich-bringing-ai-everywhere)

## Related Jobs

- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1355348-machine-learning-engineer) at **TWILIO**
- [Data Scientist](https://www.wearedevelopers.com/jobs/ext/1351648-data-scientist) at **Almedia**
- [Principal Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1706410-principal-machine-learning-engineer) at **Almedia**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/588393-machine-learning-engineer) at **Twilio**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1597388-machine-learning-engineer) at **ZEISS Group**
- [Machine Learning Engineer](https://www.wearedevelopers.com/jobs/ext/1377841-machine-learning-engineer) at **Almedia**