Weights, Bias & the Weighted Sum
The core formula w·x + b.
Weights, Bias & the Weighted Sum is a free Deep Learning Academy lesson on CoddyKit — lesson 1 of 4. You can read the complete lesson below for free — then practise it hands-on in the browser with a built-in code editor and a 24/7 AI tutor. It is part of the Deep Learning Academy learning path, one of 4 lessons in the course, and your progress syncs across the web and the CoddyKit app.
Meet the Neuron
A neuron is the tiniest unit of a neural network. It takes a few numbers in and produces one number out. That is the whole job. 🧠
Inputs Are Just Numbers
Every neuron receives inputs as numbers, like pixel brightness or a price. Anything you can measure can become an input feeding the neuron.
Each Input Has a Weight
Each input is paired with a weight that says how much it matters. Big weight means strong influence; tiny weight means the neuron mostly ignores it.
Multiply Then Add
The neuron multiplies every input by its weight, then sums the results. This running total is the heart of the weighted sum.
score = w1 * x1 + w2 * x2The Bias Shifts Everything
The bias is an extra number added at the end. It shifts the result up or down so the neuron can fire even when inputs are zero.
score = w1 * x1 + w2 * x2 + bThe Core Formula
Put it together and you get the famous line w·x + b. Weights times inputs, plus bias. Almost every layer in deep learning starts here.
Why the Dot Product
That weight-times-input sum is exactly a dot product. Writing it as w·x lets you handle two inputs or two thousand with the same idea.
Code the Weighted Sum
Here is the weighted sum in plain Python. Loop over paired weights and inputs, multiply, and accumulate the total.
score = b
for w, x in zip(weights, inputs):
score += w * xWhat the Score Means
The final number is a score: higher means the neuron leans yes, lower means it leans no. A later step turns this score into a real decision.
Weights Are Learned
You do not hand-pick weights. Training nudges each weight up or down until the neuron's scores match the answers you want.
Bias Tunes Eagerness
A high bias makes a neuron eager to say yes; a low one makes it cautious. It sets the baseline before any input arrives.
Quick Check
Let's test the core formula behind a neuron.
Recap
A neuron multiplies inputs by weights, sums them, and adds a bias: w·x + b. Weights set importance, bias sets the baseline, and the result is a score. 🎯
Frequently asked questions
Is the “Weights, Bias & the Weighted Sum” lesson free?
Yes — the full text of “Weights, Bias & the Weighted Sum” is free to read here on the web, and the Deep Learning Academy course includes 4 lessons in total. To practise it interactively (a built-in code editor and a 24/7 AI tutor) and unlock the rest of the Deep Learning Academy course, upgrade to CoddyKit PRO.
What will I learn in “Weights, Bias & the Weighted Sum”?
The core formula w·x + b. You practise Deep Learning Academy with hands-on code you run directly in the browser, and a 24/7 AI tutor answers your questions as you work through the lesson.
Do I need any experience to start Deep Learning Academy?
No prior experience is required. Deep Learning Academy on CoddyKit is structured for beginners through advanced learners; this is — lesson 1 of 4, so you can start here or from the beginning and move at your own pace.
How long does the “Weights, Bias & the Weighted Sum” lesson take?
Most CoddyKit lessons take about 5–10 minutes. Each one is bite-sized and interactive, so you make steady progress and pick up exactly where you left off across the web and the app.
Can I write and run code in this Deep Learning Academy lesson?
Yes. Every Deep Learning Academy lesson includes a built-in code editor, so you write and run real code right in your browser and get instant AI feedback — no local setup required.
All lessons in this course
- Weights, Bias & the Weighted Sum
- The Step Function & Linear Decisions
- Code a Perceptron from Scratch
- The XOR Problem: Why One Neuron Isn't Enough