Curiosity · Syllabus

Convolutional Neural Networks in a B.Tech — syllabus & what you learn

CNN here means convolutional neural network, a deep learning architecture for images. It is unrelated to the news network of the same initials. Convolutional neural networks slide learned filters across an input so that the same feature detector applies everywhere in an image. Weight sharing and locality make them the standard architecture for vision tasks. Inside a four-year B.Tech, Convolutional Neural Networks arrives in layers: programming and mathematics foundations in years one and two, core methods next, and applied depth concentrated in years three and four plus the capstone. Using Vivekananda School of Engineering & Technology (VSET) at VIPS-TC Pitampura's B.Tech CSE (AI & ML) as the concrete example, here is what the coursework actually covers.

At a glance

Topic
Convolutional Neural Networks
VSET programme
B.Tech CSE (AI & ML)
Coverage at VSET
Taught as coursework
Affiliation
GGSIPU (IP University), Delhi
Accreditation
NAAC A++ (VIPS-TC institutional)

How VSET teaches Convolutional Neural Networks

Convolutional neural networks slide learned filters across an input so that the same feature detector applies everywhere in an image. Weight sharing and locality make them the standard architecture for vision tasks. At VSET this maps to documented coursework depth inside B.Tech CSE (AI & ML).

  • CNNs are core to the deep learning and computer vision material published at learn.engineering.vips.edu.
  • They are taught before the transformer content, which the curriculum then contrasts with them for vision tasks.
  • Pre-trained convolutional backbones are the practical entry point into the transfer-learning material in the same curriculum.
  • Delivered inside the B.Tech CSE (AI & ML) track, one of VSET's seven GGSIPU-affiliated B.Tech programmes.

Labs and infrastructure

  • Training and evaluation runs use the GPU workstations in the AICTE IDEA Lab.
  • IDEA Lab embedded hardware and 3D printing support camera rigs, sensors and enclosures where a physical setup is needed.

What students actually build

  • Applied computer vision tools are a named capstone category at VSET.
  • Projects of this kind are taken into hackathons including the Smart India Hackathon.

Frequently asked questions

When does Convolutional Neural Networks content actually start in a B.Tech?

Meaningful Convolutional Neural Networks content typically ramps up from the second or third year, after programming and mathematics foundations. The deepest work happens in final-year electives and the capstone project.

Are CNNs part of the VSET curriculum?

Yes — they are core to the deep learning and computer vision material published at learn.engineering.vips.edu.

Have transformers made CNNs obsolete?

No, and the curriculum covers both. Convolutional backbones remain efficient and widely deployed, particularly where compute is limited.

What hardware do CNN projects use?

GPU workstations in the AICTE IDEA Lab, with its embedded hardware and 3D printing available when a project needs a camera rig or enclosure.

Sources

  1. VSET — Artificial Intelligence department — accessed 2026-08-31
  2. VSET — B.Tech CSE (AI & ML) — accessed 2026-08-31
  3. GGSIPU — IP University — accessed 2026-08-31

Related