Advanced everything in AI & ML, page 14
Panoptic Segmentation: A Unified View of a Scene
Panoptic segmentation unifies two tasks: it labels every pixel with a class ('stuff' like road, sky) and also identifies individual object instances ('things' like car 1, car 2). It provides a complete scene understanding for autonomous driving and robotics.
Instance Segmentation: Counting and Outlining Objects
Instance segmentation identifies and outlines each distinct object in an image, labeling 'car 1' and 'car 2' separately. It's crucial for self-driving cars tracking individual pedestrians.
Focal Loss: Forcing Models to Learn from Hard Examples
Focal Loss tells your model to ignore the easy examples during training and focus on the hard ones. This is critical for object detection, where thousands of background patches can overwhelm the few actual objects, creating a massive class imbalance.
Transfer Learning: Don't Train Vision Models from Scratch
Don't train a vision model from scratch. Transfer learning reuses a model trained on a huge dataset (like ImageNet) as a starting point for your specific task. This lets you achieve high accuracy on new image types with much less data and compute.
GoogLeNet's Inception Module: Wider, Not Just Deeper
Instead of choosing one filter size, GoogLeNet's Inception module runs 1x1, 3x3, and 5x5 convolutions in parallel. This lets the network capture features at multiple scales at once. The footgun is forgetting the crucial 1x1 'bottleneck' convolutions.
Residual Networks (ResNets): Go Deeper, Not Worse
ResNets let you train extremely deep networks by learning what to *change*, not the entire output. They use 'skip connections' to bypass layers, which helps solve accuracy degradation in deep vision models. The footgun is thinking deeper is always better.
Batch Normalization: Stabilizing Neural Network Training
Batch Normalization regulates data flow in a neural network by re-centering and re-scaling inputs to each layer. This stabilizes deep network training, allowing higher learning rates.
SLAM: Mapping a Room While You're Still In It
SLAM solves a chicken-and-egg problem: you can't map a space without knowing your location, and you can't know your location without a map. It does both at once. It's used by robots and AR headsets to navigate.
Bundle Adjustment: Jointly Refining 3D Scenes and Cameras
Bundle adjustment is a grand negotiation, simultaneously refining a 3D scene, camera poses, and lens properties to best explain the 2D images. It's the final polish in Structure from Motion (SfM) or SLAM.
Eight-Point Algorithm: Finding Geometry from Image Pairs
The Eight-Point Algorithm finds the geometric relationship between two camera views of the same scene. Given at least eight matching points, it estimates the essential or fundamental matrix.
Local Binary Patterns (LBP) for Texture Classification
LBP is a 'visual descriptor' that summarizes an image's texture into a feature set for a machine to read. It's a powerful tool for texture classification, but its performance often improves significantly when combined with other descriptors like HOG.
ORB: Fast, Free Feature Detection for Computer Vision
ORB combines the speedy FAST keypoint detector with a rotation-aware BRIEF descriptor. It offers a fast, royalty-free alternative to SIFT for finding and describing unique points in an image, even when the object is rotated.
SURF: A Faster, Patented Alternative to SIFT
SURF is a faster, more robust alternative to SIFT for finding key points in an image. It's used for real-time object recognition or stitching images where SIFT is too slow. Beware: its core algorithms are patented, limiting commercial use without a license.
Laplacian of Gaussian (LoG) for Blob Detection
LoG finds blobs by blurring an image then finding points of maximum curvature, like finding the top of a hill by looking where the slope changes fastest. It's used in medical imaging and astronomy. The footgun: the blur size dictates the blob size you can.
Affine Transformations: Move, Scale, and Rotate Without Bending
An affine transformation is a way to move, scale, rotate, or shear an object while keeping all lines straight and parallel lines parallel. It's used everywhere in computer graphics.
Canny Edge Detector: Finding True Edges
The Canny detector finds true edges by identifying sharp, connected intensity changes. It's used in object detection and feature extraction where clean edge maps are vital.
Bayer Filter: Faking Full Color with a Filter Grid
A Bayer filter is a hack for capturing color with one sensor: a checkerboard of red, green, and blue filters is placed over the sensor grid. This is how most digital cameras work. The footgun is that the raw output must be 'demosaiced' to create.
BRDF: Modeling How Surfaces Reflect Light
A BRDF is a function that describes a surface's appearance by defining how it reflects light from any incoming direction to any viewing direction. It's used in rendering engines to create materials like brushed metal or velvet.
Radiometry: Measuring Light as Physics, Not Perception
Radiometry measures light's physical power, not how humans perceive it. It's for objective energy measurement in computer vision or physics simulations, using watts, not lumens. The footgun is confusing it with photometry, which is weighted for human vision.
Extrinsic vs. In-Context: Two Types of LLM Hallucination
LLM hallucinations split into two types: in-context, where output contradicts provided sources, and extrinsic, where it conflicts with world knowledge. This distinction is critical for engineers debugging AI systems, as RAG pipelines fight in-context errors while open-ended generation faces extrinsic ones. Mitigating extrinsic hallucinations requires models to not only be factual but also to admit when they don't know an answer, a major challenge given the impracticality of verifying against tra
We are hiring for this. Every open role lists the topics its interview covers, so you can prepare for the real thing rather than guessing.
See open roles