Ep2: How TensorFlow Really Works: Tensors, Shapes & Real Business Examples

TensorFlow isn’t only “neural networks” — at the beginning, it’s a powerful tensor math engine. In this video, you’ll learn what TensorFlow is, what a Tensor is, and the key concepts that make everything work: rank, shape, dtype, indexing/slicing, reshaping, broadcasting, and aggregation (reduce operations). Then we make it practical with hands-on e-commerce scenarios using only core TensorFlow ops (no Keras, no layers). You’ll calculate daily revenue, checkout totals (discount + VAT), flag suspicious orders, find best-selling products, analyze trends using slicing, compute shipping tiers with `tf.where`, and normalize data with z-scores — all step by step in a Jupyter notebook. If you’re new to TensorFlow, this is the clean foundation you need before moving into gradients, training, and models. Code notebook used in the video: https://github.com/josedacruz/tensorf... --- Timestamps 00:00 Intro: why tensors are the real TensorFlow “basics” 03:13 What is TensorFlow (and what it’s good at) 05:53 What is a Tensor? Rank + Shape with real examples (images) 07:29 Creating tensors: `tf.constant`, `zeros`, `ones`, `range` 08:59 Shape, dtype, rank + `tf.cast` 10:43 Indexing, slicing, and `tf.reshape` (make data “fit”) 14:55 Broadcasting (tax example + matrix + vector) 16:27 Math & aggregation: `reduce_sum`, `reduce_mean`, axes explained 19:55 E-commerce Demo 1: daily revenue dashboard (reshape + reduce + chart) 23:59 Demo 2–3: checkout math + fraud threshold filter 26:35 Demo 4: best seller + heatmap (days × products) 29:01 Demo 5: trend analysis (slice last 7 days + chart) 29:59 Demo 6: shipping tiers with `tf.where` (+ rule curve) 32:06 Demo 7: normalization (z-scores) + raw vs normalized plot 34:37 Wrap-up: what you can do with TF before ML models --- #TensorFlow #TensorFlowTutorial #TensorFlowBasics #Tensors #MachineLearning #DataScience #Python #NumPy #Broadcasting #Reshape #Slicing #GradientDescent #Analytics #Ecommerce #Programming #LearnToCode #JupyterNotebook #MLTutorial #AI #GoogleAI