You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
-**Time commitment**: ~10 hours per week for coursework and projects
43
+
-**What's included**:
44
+
- Regular live office hours with instructors
45
+
- Structured learning path with deadlines
46
+
- Peer interaction and community support
47
+
- Opportunity to earn a certificate
48
+
- Access to all recorded sessions and office hours
49
+
-**Register**: [Sign up here](https://airtable.com/shryxwLd0COOEaqXo)
50
+
-**Calendar**: [Subscribe to updates](https://calendar.google.com/calendar/?cid=cGtjZ2tkbGc1OG9yb2lxa2Vwc2g4YXMzMmNAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ)
51
+
52
+
### Self-Paced Learning (Available Anytime)
53
+
54
+
All materials are freely available on GitHub. You can:
55
+
- Watch videos on [YouTube](https://www.youtube.com/playlist?list=PL3MmuxUbc_hIhxl5Ji8t4O6lPAOpHaCLR)
56
+
- Follow along with the syllabus below
57
+
- Join our [Slack community](https://DataTalks.Club/slack.html) for help and discussion
58
+
- Complete homework at your own pace (solutions included)
59
+
- Work on projects to practice what you learn
60
+
61
+
**Note**: Self-paced learning gives you access to all course materials and recordings, but you need to join a live cohort to earn a certificate.
62
+
63
+
## What This Course Is About
64
+
65
+
This is a practical course where you'll learn to build and deploy machine learning systems. We focus on the engineering side from training models to getting them to work in production.
66
+
67
+
**You'll learn:**
68
+
- Core ML algorithms and when to use them
69
+
- How to prepare data and engineer features
70
+
- Model evaluation and selection
71
+
- Deploying models with Flask, Docker, and cloud platforms
72
+
- Using Kubernetes for ML model serving
73
+
- MLOps practices
74
+
75
+
**What makes this course different:**
76
+
-**Hands-on approach**: Build real projects, not just follow tutorials
77
+
-**Practical focus**: Heavily focused on implementation over mathematical theory
78
+
-**End-to-end focus**: From data to deployment
79
+
-**Community-driven**: Learn alongside others, get help when stuck
80
+
-**Open source**: All materials on GitHub, contribute improvements
81
+
-**Free**: No paywalls, no premium tiers
82
+
83
+
**Technical setup**: For machine learning modules, you only need a laptop with internet connection. For deep learning sections, we'll use cloud resources (like Saturn Cloud) for more intensive computations.
84
+
85
+
## Prerequisites
86
+
87
+
**You'll need:**
88
+
- Some programming experience (1+ years, preferably Python)
89
+
- Basic Python knowledge: variables, libraries, and Jupyter notebooks
90
+
- Basic command line comfort
91
+
- High school math
92
+
93
+
**Helpful but not required:**
94
+
- Statistics background
95
+
- Git/GitHub familiarity
96
+
97
+
No machine learning experience needed, we'll start from the basics.
98
+
99
+
## Syllabus
100
+
101
+
### [Module 1: Introduction to Machine Learning](01-intro/)
102
+
103
+
Learn the fundamentals: what ML is, when to use it, and how to approach ML problems using the CRISP-DM framework.
104
+
105
+
**Topics:**
106
+
- ML vs rule-based systems
107
+
- Supervised learning basics
108
+
- CRISP-DM methodology
109
+
- Model selection concepts
110
+
- Environment setup
111
+
112
+
### [Module 2: Machine Learning for Regression](02-regression/)
113
+
114
+
Build a car price prediction model while learning linear regression, feature engineering, and regularization.
115
+
116
+
**Topics:**
117
+
- Linear regression (from scratch and with scikit-learn)
118
+
- Exploratory data analysis
119
+
- Feature engineering
120
+
- Regularization techniques
121
+
- Model validation
122
+
123
+
### [Module 3: Machine Learning for Classification](03-classification/)
124
+
125
+
Create a customer churn prediction system using logistic regression and learn about feature selection.
126
+
127
+
**Topics:**
128
+
- Logistic regression
129
+
- Feature importance and selection
130
+
- Categorical variable encoding
131
+
- Model interpretation
132
+
133
+
### [Module 4: Evaluation Metrics for Classification](04-evaluation/)
134
+
135
+
Learn how to properly evaluate classification models and handle imbalanced datasets.
Learn to serve ML models at scale using Kubernetes and TensorFlow Serving.
193
+
194
+
**Topics:**
195
+
- Kubernetes basics
196
+
- TensorFlow Serving
197
+
- Model deployment and scaling
198
+
- Load balancing
199
+
200
+
### [Module 10: KServe (Optional)](11-kserve/)
110
201
111
-
#### [Capstone Projects](projects/)
112
-
- Midterm & Final Projects integrating all learned concepts
202
+
Advanced model serving with KServe for production ML systems.
113
203
114
-
## Community & Support
115
204
116
-
### **Getting Help on Slack**
117
-
Join the [`#course-ml-zoomcamp`](https://app.slack.com/client/T01ATQK62F8/C0288NJ5XSA) channel on [DataTalks.Club Slack](https://DataTalks.Club/slack.html) for discussions, troubleshooting, and networking.
205
+
### [Capstone Project](projects/)
118
206
119
-
To keep discussions organized:
120
-
- Follow [our guidelines](asking-questions.md) when posting questions.
121
-
- Review the [community guidelines](https://datatalks.club/slack/guidelines.html).
207
+
Choose a problem that interests you, find a suitable dataset, and develop your model. Deploy your model into a web service (local deployment or cloud deployment for bonus points).
122
208
123
-
> We encourage [Learning in Public](learning-in-public.md)
209
+
## Community & Getting Help
124
210
125
-
## Sponsors & Supporters
126
-
A special thanks to our course sponsors for making this initiative possible!
We encourage sharing your progress! Write blog posts, create videos, post on social media with #mlzoomcamp. It helps you learn better and builds your professional network.
225
+
226
+
**Bonus**: You can earn extra points for sharing your learning experience publicly.
227
+
228
+
Learn more: [Learning in Public](learning-in-public.md)
229
+
230
+
## Certificates
231
+
232
+
To receive a certificate, you'll need to:
233
+
234
+
1.**Join a live cohort** (self-paced learners cannot earn certificates)
235
+
2.**Complete 2 out of 3 projects**:
236
+
-**Midterm Project**: Choose a problem that interests you, find a suitable dataset, and develop your model
237
+
-**Capstone Project**: Complete either Capstone Project 1 or Capstone Project 2 (includes deploying a model as a web service)
238
+
3.**Review 3 peers' projects** by the deadline
239
+
240
+
**Important**: Projects must be completed individually, and you can join after the course has started if you miss some homework deadlines.
241
+
242
+
<palign="center">
243
+
<strong>Ready to start? <ahref="https://airtable.com/shryxwLd0COOEaqXo">Join the 2025 cohort</a> or <ahref="01-intro/">start with Module 1</a></strong>
244
+
</p>
245
+
246
+
## Sponsors
247
+
248
+
Thanks to our sponsors who make this course possible:
@@ -157,5 +279,5 @@ Interested in supporting our community? Reach out to [[email protected]](mai
157
279
158
280
All the activity at DataTalks.Club mainly happens on [Slack](https://datatalks.club/slack.html). We post updates there and discuss different aspects of data, career questions, and more.
159
281
160
-
At DataTalksClub, we organize online events, community activities, and free courses. You can learn more about what we do at [DataTalksClub Community Navigation](https://www.notion.so/DataTalksClub-Community-Navigation-bf070ad27ba44bf6bbc9222082f0e5a8?pvs=21).
0 commit comments