After every year learning extends Data, AI, Products, and Domain. 2023 had a blend of experiences. Still figuring out answers for every dimension #2023 #Learnings
→ How you've adapted to industry shifts, and GenAI's meaningful adoption. Possible use cases vs relevant, meaningful production-ready use cases. Example - Newly launched section in Amazon reviews, What customers say.
→ How you've overcome engineering challenges balancing business goals. New ways to solve old problems with Foundation models. Time vs building a production-grade solution. Example - Moving away from custom NER vs Leveraging LLM Embeddings, Blend of both custom embedding + RAG, New ways of solving.
→ How your skills align with the company's vision, Learning to predict the future. New approaches and papers evolve faster than certifications. A blend of tech + and domain is key. Segment Anything model, Visual QnA, Intructpix2pix have made more vision use cases feasible Tryon, etc..
→ How you bridge the gap between tech and business, Fast yet impactful use cases, Get the basics right. Demos / New offerings vs making it to production need a careful selection of use cases / applying past experiences to get things right in the first iteration. Balance the tradeoff between creativity vs innovation vs build a product strategy vs solve a real need vs fancy demos. #learning #perspectives #solutions #datascience #MachineLearning #AI #DeepLearning
In the past 8 years Skill is a blend of product + domain + data + AI lens. Learning is more from a customer point of view vs a technology point of view. How well you build your MVP depends on product and domain clarity. With a frugal setup often it means you end up playing product, domain, data, and AI roles. Many projects have to pick up and answer the below questions as part of successful strategy and MVP.
→ How you've adapted to industry shifts, GenAI's meaningful adoption
→ How you've overcome engineering challenges balancing business goals
→ How your skills align with the company's vision, Learning to predict the future
→ How you bridge the gap between tech and business, Fast yet impactful use cases, Get the basics right
Dataset from - Pinterest and DeviantArt, e-commerce services like Shopify, cloud services like Amazon Web Services, thumbnails from YouTube, and images from news sites.
Diffusion – Noise Addition in the forward step, Denoising in the second step
Key Steps in Implementation
Method of learning to generate new stuff - Forward/reverse diffusion
Way to link text and images - Text-image representation model, Word as vectors, CLIP
Way to compress images retain features - Autoencoder - imposes a bottleneck in the network which forces a compressed knowledge representation of the original input
Priors built into the algorithm, Diffusion for Images – UNet architecture - U-net architecture + ‘attention’
ControlNet - Control diffusion models by adding extra conditions, a "locked" copy, and a "trainable" weights copy
Method of learning to generate new stuff - Forward/reverse diffusion
Way to link text and images - Text-image representation model
Way to compress images - Autoencoder
Way to add in good inductive biases - U-net architecture + ‘attention’
Build Stable Diffusion “from Scratch”
Principle of Diffusion models (sampling, learning)
Diffusion for Images – UNet architecture
Understanding prompts – Word as vectors, CLIP
Let words modulate diffusion – Conditional Diffusion, Cross Attention
Diffusion in latent space – AutoEncoderKL
Training on Massive Dataset. – LAION 5Billion
GAN
One shot generation. Fast.
Harder to control in one pass.
Adversarial min-max objective. Can collapse.
Diffusion
Multi-iteration generation. Slow.
Easier to control during generation.
Simple objective, no adversary in training.
Key Ingredients of UNet
Convolution operation
Save parameter, spatial invariant
Down/Up sampling
Multiscale / Hierarchy
Learn modulation at multi scale and multi-abstraction levels.
Skip connection
No bottleneck
Route feature of the same scaledirectly.
Cf. AutoEncoder has bottleneck
Autoencoder
Autoencoder - impose a bottleneck in the network which forces a compressed knowledge representation of the original input
An autoencoder can learn non-linear transformations with a non-linear activation function and multiple layers
An ideal autoencoder will learn descriptive attributes of faces such as skin color, whether or not the person is wearing glasses, etc. in an attempt to describe an observation in some compressed representation.
For variational autoencoders, the encoder model is sometimes referred to as the recognition model whereas the decoder model is sometimes referred to as the generative model
3D detailing (wheels, palms, pineapples and the awning)
QR code to enter a holiday contest
Information postcards on the side of the display
An exercise in beautiful simplicity that creates a valuable solution for the consumer/shopper
‘Refill & Save’ communication very effectively
Great way of communicating value beyond price
Epic festive display from Lindt in Budgens. The palletised display houses a bountiful array of SKUs and really benefits from the integral LED lighting. First class.
Get better at one thing / Future-oriented learning
Partner on complimenting skills
Expertise is Domain + Data + Tech
It's ok to stop earning but not stop learning
Be result oriented not task oriented
Do not pick something if you don't like to
Don't bother being an expert of all, Be good at a few
Build Vision + NLP + Data skills + Strategy skills
Build meaningful connections and help whenever needed / possible
Teaching
Learn by Domain knowledge - Learn within the context of a specific domain
I will teach you how to solve with AI - Providing personalized instruction and practical experience.
Build prototype / Solution options - First tangible step in transforming your ideas into reality
Tools / Data / Key drivers - Combine Expertise with Data
Build a production-grade app - Advance your prototype to a production-grade application
Enable them to solve by connecting things they don't know with things they know.
Empower your problem-solving capabilities by learning to connect new concepts with your existing knowledge, fostering innovation and independent thinking
**Introducing the all-new Kia Sorento:** a mid-size SUV that's perfect for families and adventurers alike. With its rugged good looks, spacious interior, and impressive performance, the Sorento is sure to turn heads wherever you go.
**Here are just a few of the things that make the Sorento so great:**
* A powerful 3.3-liter V6 engine that produces 290 horsepower and 252 lb-ft of torque * An 8-speed automatic transmission that provides smooth and responsive shifting * All-wheel drive for superior traction in all weather conditions * A spacious interior with seating for up to seven passengers * A long list of standard features, including a panoramic sunroof, heated front seats, and a premium audio system
**If you're looking for a mid-size SUV that offers the perfect blend of comfort, performance, and style, the Kia Sorento is the perfect choice for you.**
**Visit your local Kia dealer today to learn more about the all-new Sorento and take it for a test drive.**
Seems very much a lot of own creativity :)
Way to go, Good start but long way to goto production, Multiple human in loop iterations
In the past 8 years, independently navigated 80% of projects without product managers, leading from concept to production.
Managed plans and schedules for a 3-5 member AI/ML team, showcasing leadership in streamlined project execution.
Specialized in strategy and vision realization across multiple domains, with practical experience in point-of-view (POV) framework and minimum viable product (MVP) execution.
Successfully developed and deployed innovative products, reflecting a record of tangible achievements in product development.
The role in a few words is Product and Innovation Architect with a focus on Applied AI, reflecting expertise in driving technology solutions and product innovation.
In a startup, everyone works toward a shared goal using the best web, data, AI, and APIs, focusing on coding a cohesive user journey. Compared to big companies, where five separate teams with mixed abilities might work on overlapping projects, a startup operates with 'X' effort, whereas a large company expends '5X' with the risk of internal competition leading to inefficiencies. By the time the larger company overcomes these challenges, the startup likely has rolled out a robust set of production features.
Rate:
Efficiency and focus: Startups - 8, Big Companies - 4
Resource utilization: Startups - 9, Big Companies - 3
The ratings reflect the agility and clear focus of startups against the potential for redundancy and internal competition at large corporations.
Why a great product needs alignment at all levels is required
I had to encounter total flooding. The repair process is more like "Replace All" not "Fix what is repaired"
What perplexes me the most is the hefty repair bills quantified in figures such as 8L and 9L. I had fuel injector issues and I was informed due to fuel contamination. I had serviced/repaired whatever best possible option.
Based on whatever I learned/understood
Dismantle parts
Dry up / Clean up
Remove any rusts and apply WD40
Replace Engine, Coolant oils
Replace Spark plugs
Strip whatever was possible. The seats, floor trim and finally the carpet.
Clean up the circuit boards thoroughly by iso propyl alcohol the damages will be minimized.
Circuit repair guys help if needed
Blew hot air to all nooks and crannies which was not accessible by hand
Some electrical parts may need effort due to flooding and water stagnation
ECM
Gearbox
Electric panel
Wiring
Sparkplugs
Problem
In reality, not all cars would have suffered the same extent of damage that they slap a predetermined estimate to owners
Since every part of the car should be touched, it will take too much time, whereas these days service just means replacing whatever is possible and getting the job done within no time
If we spend some time to gauge the extent of the damage, then it will give a better picture of the whole scene.
Not sure
Injector
Gearbox changes
Airbags
We subject our vehicles to a wide range of conditions, from potholes to torrential rain. All cars, whether new or old, are susceptible to issues. Somehow did not feel this answer was reasonable not well thought through :)
Small batch size - Class-imbalanced - settings, where small batch sizes shine.
Data augmentations have an amplified impact on performance under class imbalance, especially on minority-class accuracy
Adding a self-supervised loss during training can improve feature representations
Label smoothing, especially on minority class examples, helps prevent overfitting. We adapt label smoothing for the class-imbalanced setting by applying more smoothing to minorityclass examples than to majority-class examples
A small modification of Sharpness-Aware Minimization (SAM) pulls decision boundaries away from minority samples and significantly improves minority-group accuracy
Loss reweighting. Reweighting methods assign different weights to majority and minority class loss functions, increasing the influence of minority samples which would otherwise play little role in the loss function
Label smoothing is a technique often used in training deep learning models, particularly for classification tasks. It modifies the target labels, making them a blend of the original hard labels and some uniform or prior distribution. This can lead to better generalization by preventing the model from becoming too confident about its predictions. In a class-imbalanced setting, where some classes have significantly more examples than others, label smoothing can help by reducing the model's bias towards the more frequent classes.
Label smoothing for the class-imbalanced setting python example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
In practice, label smoothing does not change the dataset's inherent imbalance but softens the target distributions by moving a portion of the mass from the peak (corresponding to the hard label) to other classes, which can help during the training of a model, preventing it from becoming overly confident on the majority class.
Loss reweighting for the class-imbalanced setting python example
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
class_weight: Optional dictionary mapping class indices (integers) to a weight (float) value, used for weighting the loss function (during training only).
Let's import the module first
from sklearn.utils import class_weight
In order to calculate the class weight do the following
CNN/FF-Nets all the outputs are self dependent Feed-forward nets don’t remember historic input data
RNN - Hidden state memory, correlation between previous input to the next input, Cell state, Forget Gate
RNN - learn to keep only relevant information to make predictions and forget non relevant data RNN - Conveyer belt
RNN Perform well when the input data is interdependent in a sequential pattern correlation between previous input to the next input introduce bias based on your previous output
Transformer
Positional embeddings - the order and position of words in a sequence
Self attention - allows each token to dynamically weigh and integrate information from all other positions
The self-attention mechanism is a type of attention mechanism which allows every element of a sequence to interact with every others and find out who they should pay more attention to.
Multi-head attention runs multiple self-attention processes in parallel, capturing diverse aspects of the data
2024, More products / Innovation with Improved Benchmarks for Domain-Specific GPT, Multimodal World, SpeedyPrototyping, ResponsibleAI and Privacy assured personalized LLM recommendations for Mental Health, Healthcare Tips
1. Improved Benchmarks from Domain-Specific GPT - Go niche with a Domain-Specific GPT. Bring your data, and domain knowledge and Build your LLM. Why settle for generic when you can bring your data and craft a model that knows your field inside out? More benchmarks and newer models both custom / open source across domains #CustomizedAI #CustomGPT
2. #Personalized answers with privacy - Welcome Personal Data + LLM for mental health, healthcare, and suggestions. Your privacy remains intact while you enjoy tailor-made advice crafted just for you. #PersonalizedAdvice #PrivacyMatters.
3. Integrated Multimodal World - It's a #Multimodal World! Knowledge isn't just text; it's Images + Text + Data. Embrace the power of combined data forms to receive enriched, multimodal insights that tell the complete story for recommendations, personalization. #MultimodalKnowledge #HolisticAI
4. #SpeedyPrototyping - Supercharge your innovation engine with Ideas an ensemble of Models. Watch your prototyping speed take off as diverse AI models converge to refine your visions faster than ever! #SpeedyPrototyping #AIEnsemble
5. #ResponsibleAI Model building and solutioning - It's not just about building models; it's about building them right—robust, reliable, and fair. For all infrastructure providers, LLM training vendors, evaluators, and advocates for responsible AI, your insights are invaluable. #AIEthics #ResponsibleAI #GenAI #LLM #Domains #2024 #Predictions #perspectives
Welcome Visitor,
I have 20 years of experience (Coder - Emprical Learner - Teacher). I am currently working on Data Analytics (Video-Image-Text-Data) / Database / BI space. I dabble with "Data". Ping me or send a request to connect if what I do appeals to you and you want to talk about it (Data Science / Databases / Deep Learning / Architecture / Design Discussions / Consulting Projects/ Machine Learning Training's/ Strategic Leadership Roles).
Personal Goal - Reach / Teach up to 10 Million Students through various mediums (Catalyst between Academics and Industry)
My request to readers, Hope you find the posts, code snippets, notes helpful, please share your learning with others. We can only grow only by learning and teaching.
6+ years in AI, AI experience working on Image, Video, Text, Numbers - Data
15+ years in Databases
10+ in developing, deploying, monitoring large scale solutions in Supply Chain, Retail
Its my personal blog. The objective of this blog is to bookmark/share my learning's. Posts reflect my opinions, perspectives and interests. Blog post presented are my personal views and do not represent my employer's view. I have acknowledged all posts with References/Bookmarks.
For questions/feedback/career opportunities/training / consulting assignments/mentoring - please drop a note to sivaram2k10(at)gmail(dot)com
Coach / Code / Innovate
