Gallery

Contacts

405 W. Greenlawn Ave Lansing, Michigan 48910

contact@techjacksolutions.com

+1-616-320-4064

Foundations learning vertical
Track 01 · Foundations Intermediate ~8 min

How do neural networks work?

Loosely inspired by the brain, a neural network is just layers of simple units that multiply, add, and decide. Learn the single neuron, how layers stack into "deep" learning, how a prediction flows through, and the network families behind modern AI — right here on the page.

Module progress
0%

01The shape of a neural network

Picture an assembly line where information goes in one end, gets handed from station to station, and comes out the other end as an answer. A neural network works like that: it's built from rows of small workers called neurons, each doing one tiny bit of arithmetic and passing the result on. Those rows are called layers — data enters the input layer, flows through one or more hidden layers, and leaves through the output layer as a prediction. When a network has many hidden layers, we call it "deep" learning — that depth is what lets it learn complex patterns. Toggle the diagram to see a shallow network grow deeper.

WalkthroughAdd hidden layers
1
hidden layer

A shallow network: 3 inputs → one hidden layer of 4 neurons → 1 output. Every line is a connection carrying a weight.

  • Neurons are organized in layers: an input layer, one or more hidden layers, and an output layer.
  • Each line between nodes is a connection with its own learned weight — that's where the network stores what it knows.
  • "Deep" learning simply means many hidden layers — more depth, more capacity to model complex relationships.

02Inside a single neuron

Every network is built from one repeated unit. A neuron takes inputs, multiplies each by a weight, adds a bias, sums them, then passes that sum through an activation function to produce its output. Tap each part to see what it does.

ExploreTap a part
A single neuron
Neuronthe unit
Weights & biaslearned numbers
Activationthe decision
Layersneurons grouped
The basic unit

Neuron

A neuron is the network's smallest building block. It receives one or more inputs, does a small calculation — multiply each input by a weight, add them up with a bias, then apply an activation function — and emits a single output number that feeds the next layer.

InteractiveDrag the sliders — watch the neuron compute
0.6
0.7
0.9
-0.4
0.3
0.5
-0.2

Edge thickness = weight size · blue = positive, red = negative. The neuron only "fires" a positive value (ReLU zeroes negatives).

03The forward pass: how a prediction is made

Making a prediction is called the forward pass: data flows from the input layer, through each layer's weighted sums and activations, to the output. Step through one neuron computing its output, then the signal moving to the next layer and out as a prediction. (Numbers shown are illustrative, to make the arithmetic concrete.)

WalkthroughStep or run the forward pass
Perceive inputs
Inputs arrive. The input layer receives the raw values — e.g., three numbers x₁, x₂, x₃ describing one example.
Weighted sum
Multiply & add. Each input is multiplied by its weight and summed, then a bias is added: z = (x₁·w₁ + x₂·w₂ + x₃·w₃) + b.
Activation
Decide. The sum z passes through an activation function (e.g., ReLU) to produce the neuron's output a — adding the non-linearity that lets networks model curves, not just straight lines.
Next layer
Propagate. That output becomes an input to every neuron in the next layer, which repeats the same multiply-add-activate — layer by layer.
Output
Prediction. The output layer turns the final activations into the answer — a class label, a probability, or a number. That's the forward pass complete.
  • The forward pass only uses the weights — it doesn't change them. Learning happens separately, during training.
  • Without activation functions, stacking layers would collapse to a single straight-line model — the non-linearity is what makes depth useful.

04How a network learns: training in one breath

A fresh network's weights start as essentially random, so its first predictions are wrong. Training fixes that. The network makes a prediction, that prediction is compared to the correct answer to measure the error — a number called the loss. Then backpropagation works backward through the layers to figure out how much each weight contributed to the loss, and gradient descent nudges every weight a small step in the direction that reduces the error. Repeat this over many examples, many times, and the weights gradually settle into values that make good predictions. That repeated "predict → measure error → nudge weights" loop is the whole of how neural networks learn.

05The main families of network

"Neural network" is an umbrella term. Different architectures wire neurons together in different ways to suit different data. The four you'll meet most:

ExploreSwitch family

Feedforward — the basic network

The simplest design: data moves in one direction only, input → hidden → output, with no loops. It's the forward pass you just stepped through. Great for straightforward prediction and classification on fixed-size inputs, and the foundation every other architecture builds on.

flow: input → hidden layers → output
good for: tabular data, simple classification

CNN — convolutional, great for images

A Convolutional Neural Network slides small filters across an image to detect local patterns — edges, then textures, then shapes — building up to whole objects. Because it reuses the same filters everywhere, it's efficient and excels at vision tasks.

good for: images, video, spatial data
idea: local filters detect patterns anywhere

RNN — recurrent, built for sequences

A Recurrent Neural Network processes data in order and keeps a running internal state, so earlier items influence later ones. That memory of position makes it suited to sequences and time — text, audio, or any series of steps.

good for: sequences, time series, language
idea: state carries context across steps

Transformer — attention, powers modern LLMs

A Transformer uses a mechanism called "attention" to weigh how much every part of the input relates to every other part — all at once, rather than strictly in sequence. That ability to model long-range relationships is what powers modern large language models.

good for: language, large-scale models (LLMs)
idea: attention relates every token to every other

06Check your understanding

TJS Quiz
window.onload=function(){window.print()}<\/scr'+'ipt>'; var w=window.open('','_blank'); if(w){ w.document.write(html); w.document.close(); } } function accentHex(){ var v=getComputedStyle(root).getPropertyValue('--tjq-accent').trim(); return v||'#2095e9'; } function dlCanvas(cv){ var a=document.createElement('a'); a.download=(D.id||'quiz')+'-result.png'; a.href=cv.toDataURL('image/png'); a.click(); } function shareCard(pct,cat){ var cv=$('#tjqCardCv'); if(!cv||!cv.getContext) return; var x=cv.getContext('2d'),W=cv.width,H=cv.height,acc=accentHex(); var g=x.createLinearGradient(0,0,W,H); g.addColorStop(0,'#0E1F40'); g.addColorStop(1,'#10294f'); x.fillStyle=g; x.fillRect(0,0,W,H); x.save(); x.globalAlpha=.16; x.fillStyle=acc; x.beginPath(); x.arc(W*.85,H*.16,160,0,7); x.fill(); x.restore(); x.fillStyle='rgba(255,255,255,.55)'; x.font='600 21px DM Sans, sans-serif'; x.fillText('TJS QUIZ · AI KNOWLEDGE HUB',58,76); x.fillStyle='#fff'; x.font='700 60px Fraunces, serif'; x.fillText(D.topic||'Quiz',56,168); x.fillStyle=acc; x.font='700 28px "Space Mono", monospace'; x.fillText(String(cat||'').toUpperCase(),58,H-150); x.fillStyle='#fff'; x.font='700 104px "Archivo Black", sans-serif'; x.fillText(pct+'%',54,H-52); x.fillStyle='rgba(255,255,255,.55)'; x.font='400 21px DM Sans, sans-serif'; x.fillText('scored on the '+(D.topic||'')+' quiz',58,H-22); x.strokeStyle=acc; x.lineWidth=8; x.strokeRect(0,0,W,H); if(cv.toBlob && navigator.canShare){ cv.toBlob(function(blob){ try{ var file=new File([blob],'quiz-result.png',{type:'image/png'}); if(navigator.canShare({files:[file]})){ navigator.share({files:[file],title:'My quiz result',text:'I scored '+pct+'% ('+cat+') on the '+(D.topic||'')+' quiz.'}).catch(function(){dlCanvas(cv);}); return; } }catch(e){} dlCanvas(cv); }); } else dlCanvas(cv); } function certPrint(pct,cat){ var raw=(($('#tjqCertName')||{}).value)||''; var name=esc(raw.trim()); var ds=new Date().toLocaleDateString(undefined,{year:'numeric',month:'long',day:'numeric'}); var id='TJQ-'+String(Math.floor(Math.random()*1e9)); var acc=accentHex(); var html='Certificate
Certificate of Completion

'+esc(D.topic||'Quiz')+'

This recognizes

'+(name||'—')+'

for completing the assessment at the '+esc(cat)+' level ('+pct+'%).

'+ds+' · TJS AI Knowledge Hub · ID '+id+'

A self-assessment summary recognizing completion of an educational module — not a professional certification.

window.onload=function(){window.print();}<\/scr'+'ipt>'; var w=window.open('','_blank'); if(w){ w.document.write(html); w.document.close(); } } renderStart(); })();

07Take it with you & go deeper

"Neural networks in 5 minutes" — one-page summary
The whole module distilled to a printable cheat-sheet.
▸ Coming next — deeper progression (specced & grounded)
Coming soon

How training & backpropagation work

Loss functions, gradients, and the predict → measure → nudge loop, step by step.

In the pipeline
Coming soon

Transformers explained

Attention, tokens, and why this architecture powers modern large language models.

In the pipeline

Continue learning

Sources & review

Published by Tech Jacks Solutions · Reviewed June 2026. This lesson explains established concepts and is grounded in the references below; figures shown in the interactives are illustrative and labelled as such.

How neural networks work — in 5 minutes

Tech Jacks Solutions · AI Knowledge Hub · educational summary

The single neuron

A neuron takes inputs, multiplies each by a weight, adds a bias, sums them, then passes the sum through an activation function to produce one output. It's the network's smallest building block.

Layers

Neurons are grouped into layers: an input layer, one or more hidden layers, and an output layer. "Deep" learning means many hidden layers — more depth, more capacity to model complex patterns.

The forward pass

To make a prediction, data flows input → through each layer's weighted sums + activations → output. Each neuron's output feeds the next layer's inputs, layer by layer, until the output layer produces the answer.

Training

The prediction is compared to the correct answer to measure error (the loss). Backpropagation finds how each weight affects the loss, and gradient descent nudges the weights to reduce it. Repeat over many examples until predictions are good.

Network families

Feedforward — basic, one-way flow. CNN — convolutional, great for images. RNN — recurrent, for sequences/time. Transformer — uses "attention"; powers modern LLMs.