This little girl wanted to travel all around the world and make a difference.
This little girl felt different growing up, and didn’t have many friends. However, she has always been fascinated with meeting interesting people, getting to know their stories and learning from them.
She was a very curious kid, always a million questions running in her head. Could beat most people at a game of chess!
She never really thought she could achieve much, bullied in school by some peers, she developed a very low self esteem which took years to overcome.
But hey, she never gave up on things.
She walked a completely different path, involved in the launch of the first all student satellite in India, went to present a research paper during undergraduate, solo trip across Europe (from India) when 19 and then doing the final semester of undergraduate abroad studying computational neuroscience.
Now she works on climate change, mental health and female representation in technology.
This little girl is me.
On this International Day of the Girl Child, a piece of advice I would have given myself and any other girls:
Embrace your shortcomings and to learn from your mistakes; they make you who you are meant to be! Dream big, and trust yourself!
TensorFlow is an end-to-end open source platform for machine learning. It has a comprehensive, flexible ecosystem of tools, libraries and community resources that lets researchers push the state-of-the-art in ML and developers easily build and deploy ML powered applications.
– It is optimized for speed, & makes use of techniques like XLA for quick linear algebra operations.
– Responsive Construct : we can easily visualize each and every part of the graph which is not an option while using Numpy or SciKit.
– Flexible: it is flexible in its operability, meaning it has modularity and the parts of it which you want to make standalone, it offers you that option.
– Easily Trainable: It is easily trainable on CPU as well as GPU for distributed computing.
– Parallel Neural Network Training: it offers pipelining in the sense that you can train multiple neural networks and multiple GPUs which makes the models very efficient on large-scale systems.
– Large Community: it has been developed by Google, there already is a large team of software engineers who work on stability improvements continuously.
– Open Source (yay): the best thing about this machine learning library is that it is open source so anyone can use it as long as they have internet connectivity.
– Also in TensorFlow we can use TPU’s (Tensor Processing units) with the help of custom models and custom training loops when it comes to Distributed computing. One can try out TPU for their custom trained model on Colab.
Uses of TensorFlow?
You are using TensorFlow daily but indirectly with applications like Google Voice Search or Google Photos.
All the libraries created in TensorFlow are written in C and C++. But has a complicated front-end for Python. Your Python code will get compiled and then executed on TensorFlow distributed execution engine built using C and C++.
The number of applications of TensorFlow is literally unlimited and that is the beauty of TensorFlow.
Hey! Let’s take a minute now and think if we really can grow in the comfort zone, and if you are still in your comfort zone, what is it?
To me personally, as I was an introvert growing up, I always refrained from trying anything – I used to go to school, come back home and repeat. See – there is no room I gave myself to grow.
I was subconsciously keeping myself from doing anything I definitely was capable of.
Please read the quote above – so these are going to be some key elements of this blog – when you talk about creativity, you talk about new ideas, new perspectives, innovations, trying out things, etc. – which can rarely happen if you never think outside your comfort zone. Once you understand the need to step of it and that comfort zone is a subconscious state of mind, you are exposed to so many new perspectives, new experiences (you may love some, like some and dislike some), but you will find your calling, and realise what you actually real want (personally and professionally). And this needs you to conquer your fears .
Now, let’s talk a little bit about the comfort zone itself and what it actually is?
The phrase ‘comfort zone’ was coined by management thinker Judith Bardwick in her 1991 work Danger in the Comfort Zone.
A comfort zone is a psychological state in which things feel familiar to a person, and they are at ease, and in control of their environment, experiencing low levels of anxiety and stress.
And all of us know that’s not how life usually is. So let’s focus a little bit on this diagram here, which shows 4 zones, namely the comfort zone, the fear zone, the learning zone and the growth zone.
So when leaving the comfort zone, fear doesn’t necessarily equate to being in the panic zone. As the below diagram shows, fear can be a necessary step in order to go to the learning and growth zones:
Now, comes the most important point, how would you go from comfort zone to the fear zone? The answer is : Courage.
In fact Courage comes first. Courage is the secret ingredient which lets you act despite your fears. Courage gives you the ability to put aside your fear of failure and take the first steps. Courage helps you overcome the fear of rejection and attempt things that you have not tried before. Confidence is the outcome. It takes courage to step from the comfort zone into the fear zone. It’s very normal to be anxious while doing so, yet it would be so rewarding when you enter the learning zone, this is where you learn skills, deal with new challenges, and gain the confidence as a result of those activities.
After a learning period, a new comfort zone is created, or your own comfort zone is extended. And when you see yourself setting new goals for yourself, celebrating something (even a small achievement of yourself), you are in your growth zone. There can also be some behavioral changes you feel along the way and it’s important to be self-aware of how far you’ve come 🙂
And I personally find this diagram extremely accurate. I have been through all the stages of it.
Comfort zone – My regular life until the day I wanted things to change. Going to school, coming home and repeat.
Fear zone – When I thought how to exactly change and the efforts required. And i feared the outcomes if things went wrong
Learning zone – When I acted on what I had planned previously and was experiencing things myself (for eg, my solo trip, some of my internships), and I still continue to be in the learning zone as you learn new things every single day.
Growth zone – I think I am in the growth zone right now, because I believe you grow as you learn. So for me, the comfort zone has expanded and I consider myself somewhere in the intersection of learning and growing, which always go side by side in my opinion.
Why should we step out of our comfort zone, or why expand it? Right.
There are a few key reasons for that; Stanford psychologist Carol Dweck’s (2008) work on mindsets marked a paradigm shift in the field of positive psychology. According to her, a mindset is a self-perception or “self-theory” that people hold about themselves. Dweck’s educational work centers on the distinction between “fixed” and “growth” mindsets. According to Dweck, “In a fixed mindset, people believe their basic qualities, like their intelligence or talent, are simply fixed traits. Alternatively, in a growth mindset, people believe that their most basic abilities can be developed through dedication and hard work—brains and talent are just the starting point. This view creates a love of learning and a resilience that is essential for great accomplishment.
The second point is that expanding your comfort zone will make you stronger and more resilient as a person, who is able to tackle new challenges, you tend to be more adaptable, even when life becomes unpredictable.
It also helps a lot with self-efficacy, which is, as mentioned by Albert Bandura (1997), the belief in being able to execute necessary actions in service of a goal. Leaving the comfort zone means a phase of trial and error, during which at least some level of success is inevitable. Experiencing this success builds our self-efficacy, with belief in our ability starting to grow.
New opportunities and experiences – it allows you to gain new experiences, improve your skills and take advantage of opportunities for professional and personal growth.
For many, self-actualization acts as a powerful incentive to leave the comfort zone. Self–actualization is the complete realization of one’s potential, and the full development of one’s abilities and appreciation for life. This concept is at the top of the Maslow hierarchy of needs.
How to come out of your comfort zone can be quite subjective, but a few things that personally helped me are :
Also, sometimes it’s okay to sit back and relax in your comfort zone, recharge yourself, give yourself a little break.
It’s important to identify what are the areas in life (or bottlenecks) where staying in your comfort zone is doing more harm than good. And once you have realised that, make use of that intuition and make the changes you think are required.
Obviously it’s very important to take small steps, and celebrate the little wins, they also give you the courage to take a slightly bigger step the next time, set goals, prioritise so that you are not in panic or anxiety driven situation, communicate, talk to people you trust (or talk to me if you want) about your problems, success, etc., ask for help anytime you need it.
And always remember that your subconscious mind determines your comfort zone and it’s you who can control it, not the other way around. Our brain is extremely malleable and we can shape it however we want.
If you want to listen to me speaking about this topic – feel free to do so 🙂
You might have noticed your brain ticking and giving you signals when someone is not trustworthy.
I was pleasantly surprised to see its relationship with ventral striatum (which is a part of basal ganglia) of the brain, and stress hormones like cortisol and oxytocin. It’s all science, as I expected!
“In the new study, participants thought they were playing an economic investment game with a close friend, a stranger or a slot machine. In reality, they were playing with a simple algorithm that reciprocated trust 50 percent of the time. The researchers developed a computational model that predicted each player’s decision for each round given their previous experiences in the game.
Results showed that participants found positive interactions with a close friend more rewarding than interactions with a stranger or slot machine, and that the researchers’ “social value” model predicted participants’ investment decisions better than models that only considered financial payoffs.
Neuroimaging also showed that specific brain signals — in the ventral striatum and medial prefrontal cortex — correlated with social value signals when the participants made their decisions.
The ventral striatum is a key pathway in reward processing, while the medial prefrontal cortex is associated with representing another person’s mental state. Together, these regions provide additional evidence that players receive a greater social reward signal when they learn their friend reciprocated than the other two players in the game. This occurs despite participants learning that each player is only reciprocating 50 percent of the time. But because players receive this additional reward signal, they end up trusting their friend more than the other players throughout the game.”
The image shows: Bilateral activation in the amygdala, left ventral striatum and right dorsal striatum as a function of participants’ investment choices during the delivery of their outcomes. The color map defines the strength of the contrast’s T-scores (Statistical maps with an initial threshold of uncorrected p < 0.001 were established and were subsequently corrected for multiple comparisons using a Family Wise Error corrected cluster threshold of p < 0.05).
Personality weaknesses or character flaws cause mental health problems. People with mental health problems can snap out of it if they try hard enough.
That’s what someone said to me. Do you think that’s true?
Well, first off. Every one has some or the other personality flaw (when we look at it from other people’s lenses). It is most often that personality flaw that makes unique.
So, anyone who thinks the person who suffers from a mental health disorder is the one actually at fault – I am sorry, but that’s mostly incorrect.
The most common reason for mental health problems are:
– Biological factors, such as genes or brain chemistry : Experts believe many mental illnesses are linked to abnormalities in genes and the way genes interact with the environment. This is unique for every person (even identical twins).
– Life experiences, such as trauma or abuse : Mental illness itself occurs from the interaction of multiple genes and other factors — such as stress, abuse, or a traumatic event — which can influence, or trigger, an illness in a person who has an inherited susceptibility to it. This susceptibility often depends on the way genes in the human brain interact with each other (and is unique for each person).
– Family history of mental health problems : Mental illnesses sometimes run in families. That basically mean that sometimes people who have a family member with a mental illness may be a little more likely to develop one themselves. Susceptibility is passed on in families through genes.
Let’s support those who are suffering, instead of questioning them. A little help or care goes a long way.
We have a couple of choices here; we either ignore such statements and move OR we raise a voice. And you know, I choose the latter.
I do not want anyone going through discrimination, more mental abuse and the worst part ‘facing the stigma’ – just because they are going through some mental health issues.
And, I wish to do it for anyone who suffering ‘silently’ with a smile on.
Do we discriminate against someone with a broken leg? No, we help them. That’s absolutely noble, human and great!
But then just because we cannot see someone’s mental trauma, does that mean that we create this stigma surrounding it that makes it so impossible to talk about? And, let alone helping someone who is already suffering, we make it unbelievable for them to even talk about their emotions or issues openly?
I mean, are we really that shallow?
To anyone going through any mental health problems right now. There’s something I will like to say, from my personal experience.
Please don’t suffer in silence. I know it may be overwhelming at first to decide to take that step to seek professional help, but it will only be better from there.
Communicate what you are feeling with someone you trust.
Mental health disorders give you superpowers.
If you overthink the bad, and that makes you anxious. It also makes you think more and make your work unique. Add that extra bit of sparkle that separates you from others.
Everything has two sides. Even something that’s as dark to live with as depression or anxiety.
Let’s try and find that bit of positivity when we’re going through tough times.
A little bit of optimism, love and support goes a long way in mental wellness.
In my experience, one of the biggest opportunities for AI in the field of neuroscience is doing more biologically plausible research and creating a visual perception of the unique features of human cognition. That will lead us in understanding and knowing so much more about the human brain which still is a mystery to a huge extent. This also eventually will lead us to understand mental illnesses, triggers to mental illnesses and the best way to recover from them.
Biologically-inspired artificial neural networks and computational neuroscience approaches that attempt to elucidate brain networks are gradually getting closer to experimental neuroscience. However this would definitely require a lot more research and more conversations and collaborations between neuroscientists and AI researchers. It’s very fascinating how both can learn from each other and develop even further.
How can neuroscience benefit from AI?
As we all know, brains are far too complex for us to understand at present. I read a book called “The Psychopath Inside” by James Fallon, where he explains the brain in terms of a 3*3 rubik’s cube (it’s still so impossibly difficult to understand and visualize without prior knowledge). This is where AI jumps in according to me, and can be employed in a number of ways. Using AI we can produce new tools or applications to come up with connections or general theoretical principles. This will help us understand the complex machine that our brain is.
Also, on a more logical level AI can help us visualise the different patterns in a brain and try to find the underlying reason for the difference in patterns (as well as analyse the effects). For example; certain types of overlapping in the brain cause people to lose memory for a short duration of time – this can be visualised and studied using Recurrent Neural Networks (RNNs).
We can also visualise using AI driven tools, what part of the brain is getting affected to understand more about different mental illnesses which also might co-occur, diseases like depression, PTSD, OCD, schizophrenia, etc., by analysing what parts of the brain are more active and which ones are not.
Also, the modern neuroscience tools such as multi-electrode arrays, real-time imaging, Functional magnetic resonance imaging (fMRI), etc., produce massive amounts of dataset which depend on AI to be analysed and dealt with.
How can AI benefit from neuroscience?
Neuroscience has always been a key inspiration behind the history and development of artificial intelligence and of course there is still so much to learn from it. Neuroscience has always been an inspiration to make the network more intelligent and human-like. There are two key points to it: One is that the Artificial neural networks try to replicate or imitate human intelligence. Now with ideas comes a structure in which you would envelope your idea, that’s the second key point here; artificial networks also tend to mimic the brain structure. Transformations made using AI are breaking the internet nowadays. We hear how reliable and accurate AI is getting, however it still has a lot to learn from our brain/neuroscience.
As AI networks are inspired by the structure of a human brain, so are the neurons in the neural networks. The neural networks in AI have very similar characteris when compared to the biological neurons in a human brain. The basic working mechanism is that when one neuron cell gets activated, it generates a spike and sends signals to other neurons. In the artificial neural networks, which also have interconnected neurons, when a neuron receives an input, it gets activated and passes on the information to the other neurons. It works very similar to our brain, in a simple example – we keep getting better at the task we perform often in real life. In a similar way we train the AI on a lot of data. The artificial neural network has X number of connections and Each connection on the neural network is associated with a weight . Weight decides how much influence the input will have on the output. Biases, which are constant, are an additional input into the next layer that will always have the value of 1. During the training process, we tune the weight from node x to node y as required. However, there’s a lot to learn about the plasticity and the malleability of the human brain and try and implement them into AI networks. It is an ongoing research to make AI more human-like and more versatile. For example: As a human, I can walk even with my eyes closed. But for the AI model to do the same task in a new environment (‘walking’ with ‘eyes closed’), will probably not work well.
AI if used correctly and cautiously is very promising both is understanding the complex mental health diseases and even transforming mental healthcare.
AI can be very beneficial in predicting and classifying mental health disorders. It can also help subgroup them based on mood disorders, anxiety disorder, or if they are co-occurring (as for example depression which is an anxiety disorder can occur with a mood disorder) etc. Also, AI can potentially achieve high accuracy, as we keep developing more robust and advance AI techniques, it will be possible to help mental health practitioners re-define mental illnesses more objectively than currently done in the DSM-5, identify these illnesses at an earlier or prodromal stage when interventions may be more effective, and personalize treatments based on an individual’s unique characteristics.
Obviously, this needs to be done with a lot of caution and a lot of research is required for the same. I also believe the amalgamation of AI into identifying mental health illnesses could also reduce the stigma surrounding it, as it is still an issue that’s refrained upon in a lot of parts of the world. When we analyse it using advanced neuroscience tools and using AI, it might be sought after as a more acceptable illness, or something closer to a physical diagnosis.
I believe AI has huge potential in research, healthcare (mental and physical), and everything basically. When implemented with caution, ethics, transparency and explainability – it will do wonders!
Hoppas att du gillade det, tack! (Hope you liked it, thank you!)
– It is so easy to code on Python (and even learn). Comprehensively understanding and learn basic Python syntax is very easy, as compared to other popular languages like C, C++, and Java. However, mastering the packages, concepts and modules will take some time.
– Python is as simple to read and understand as English. No semicolons, no brackets (I love this language)!
– I love how portable it is. If you write the code on a Mac, and want to run it on windows or Linux; boom; pull out the code and run it – without making any changes to it. How awesome is that?
– Python being high-level makes it easier as we (as programmers) don’t have to remember the system architecture.
– Support for the GUI or Graphical User Interface. It’s so user-friendly in Python.
– It is so easy to write, just in a few lines of code, we can perform complex tasks.
– Python is not converted into computer code before it is run, as it is an interpreted language. There is no compilation step in Python.
– Also, the development cycle (edit/test/debug) goes faster. However as every coin has two sides, this awesome speed of development does come at a cost: once constructed, a Python program typically runs slower as compared to Java or C++. Java or C++ could be several times faster, although, at workplaces where the speed of development is essential, Python shines!
– It is open source!
– It is interpreted (code runs line by line and not the entire code at once).
– It supports both object-oriented and procedure-oriented programming.
– And Python has AMAZING libraries! For each and every purpose you want.
Not that I think I have accomplished something, but I wanted to share how it all started for me.
For me, and when I say me – I mean this ‘meh’ boring introvert who no one gave a fuck about. I always thought I was not even average, had zero confidence, had one hobby and two friends.
I was happy when alone, loved walking by myself (listening to some Eminem and some Metallica).
Sometimes I thought no one wants to hang out with me, as if I wasn’t important enough. Since I remember. Maybe that was true. I don’t care anymore to be honest, because that’s past and I have probably grown out of it.
I thought no one cared about my opinions, my thoughts, my ideas, my vision or even my existence.
Maybe I was forced to being an introvert. And a huge contributor towards that was my abusive childhood. The scars from childhood take longer to heal, you start assuming that’s how the world is, and you are scared of each and every person you meet.
Slowly, very very slowly, I realised that’s not the case, and I wanted to see more of the world.
Spent 6 weeks in Europe, and interacted with more strangers than I had ever done before (yess, even when I lived in India, where finding people is not so difficult, you know).
I had the most amazing time in the conference, trying to push the moon!
In a non-cliche way, it taught me how much is to life if I step outside my shell of some unfortunate past experiences. And slowly, one day at a time, I started to overcome the gazillions of fears I had. (I still have some, but they are more like pet-peeves as opposed to fear).
Then I had this most amazing time in Sweden, which I have talked about enough, haha.
I guess, the key is to take small steps. Very tiny steps, and being aware of the changes it may bring in your life (not freak out when you actually see those changes occurring). I sometimes ‘mansplain’ so bear with me. Also, isn’t life all about learning?
I am still the introverted girl I was before, but I know when to come out of my comfort zone, and when to slide back in! 😀
And in my opinion that’s all it is about.
I write as I hum the following;
“Imagine there’s no heaven It’s easy if you try No hell below us Above us, only skyImagine all the people Livin’ for today Ah Imagine there’s no countries It isn’t hard to do Nothing to kill or die for And no religion, tooImagine all the people Livin’ life in peace You may say I’m a dreamer But I’m not the only one I hope someday you’ll join us And the world will be as one.”
Thank you reading me blabber this, I hope it was at least slightly helpful, or motivating.
Case 1: Imagine student A, studying hard for the exam and they get good grades because of that.
Case 2: Now imagine student B, spending time on YouTube watching PewDiePie trying to save Sven and failing as they did not study at all, of course.
Throughout our lives, we have such interactions, and they are often attached to a positive or a negative outcome, right?
There are many such situations where our behaviour directly influenced by incentives or punishment. All of our actions are influenced by an incentive to gain something in return for our efforts.
Inspired by this system of getting incentives, we keep exploring and try to discover which action might lead to better rewards. In this entire process, there’s no one watching us, supervising us or mentoring us; we act solely based on our gut and we perform the action iteratively to see the results, and if they are any better than the previous time. Taking that feedback into consideration, we improves our steps, ideas, etc., and move closer towards our aim.
That’s how humans work, right?
This is what we called Reinforcement Learning (RL), also known assemi-supervised learning model in the terminology of machine learning.
We can pick like 1000s of examples of RL from real world;In football / soccer games, let us say that the environment is partially observable, since players in Team A will not be aware of Team B player’s strategies, positions, and speed of the ball. They act according to their intuition and constantly improve. That’s reinforcement learning, right there!
Key Points in Reinforcement Learning
Input: The input should be an initial state from which the model will start
Output: There are many possible output as there are variety of solution to a particular problem
Training: The training is based upon the input, The model will return a state and the user will decide to reward or punish the model based on its output.
The model keeps continues to learn.
The best solution is decided based on the maximum reward.
What are they used for?
RL Models are used for planning: That means it helps in predicting future states and possible rewards, which is dependant on the path taken. Please note that the path taken (or the choices that will be made) can be decided beforehand without experiencing the environment.
In model-based RL, the agent does not possess a priori model of the environment but estimates it while it is learning. In the learning process, it performs least number of interactions with the environment and tries to construct a model. After inducing a reasonable model of the environment, the agent then applies dynamic programming-like algorithms to compute the policy. In contrast in model-free RL, agents learn the model by trial and error process. It learns directly from experience, performs an action, collects the reward (positive or negative), then updates the value functions.
Let’s look at an example, players Me (Smriti) and you (You) are playing a chess game.
Smriti makes the first move then You make a move, again Smriti makes a move and after a certain period Smriti discovers that few of her moves were not good enough. She lost the game but she learns from her mistake. However, if Smriti simulated her moves in her brain after observing a few moves of her opponent and prepared a model and played accordingly then the outcome would have been different!
Let’s talk about the rest of the technicalities in the next blog!
To me – it’s everything. It’s my end goal, it’s the equivalent of success to me, it’s what I am seeking.
A small word right? Let me tell you want it means to me. To me, freedom is the choice to make my own decisions, the choice to say ‘naah’ and not question myself afterwards. (If you know what I mean)
And most importantly, freedom is what I feel when I travel SOLO.
That’s when I feel the most like myself. Travelling like a complete nomad, with rucksack on my back, eating cheap food, sleeping in the dorms, going to bars and dancing fuck out. Meeting strangers, who turn friends, and who stay friends for years! Trying food from different cultures, in different countries. Exploring new places, and getting lost sometimes. Ah, that’s freedom to me!
Doing what I love is freedom.
It need not to be something as big as going on a solo trip. It could be me just stealing some time from a hectic work day to read something I really enjoy. (while drinking Coca Cola, of course)
Or well, sometimes it could just be drinking Coca Cola with some people I love.
Ain’t it simple?
So freedom = success for me, which is simple; so I am successful? I guess so.
I mean for me; it’s more like 1+1-1-1+1=1; rather than 2+3-4+6+1-7=1. What I mean is, there are setbacks (the -1s) but you’ll bounce back and definitely achieve what you want, just some smart & hard work (after you identify your true calling).
And if I did the math wrong, that does NOT mean I am a robot, that’s just means that I am not as smart as I have written below, so stay tuned until the end – and don’t scroll down and cheat. ( I am trusting you guys with this, literally)
I mean, I guess all us are pretty successful, we’ve been all fighting our battles, mentally, psychically, emotionally. We have our own definitions for success.
Also, regarding success, I personally like to keep the bar low. As another thing I have learnt about success is, that it’s temporary. So I’d rather do those small things over and over again and feel successful, rather than waiting for that one dream of mine to come true. A very personal opinion though.
What I mean by this is, maybe I want to win the best AI scientist award, and I get it (claps please), and soon someone else will. It can’t lead to daily motivation. Goals that high, in my opinion are great to have, but success actually lies in much smaller things. Again, it’s a very personal opinion, and I respect everyone’s opinion, and perspective on it.
P.S. – Naah, I am not rich, I am just smart (hahaha, joking) – went to present a paper in Europe on a completely sponsored trip. Loved it so much, that I decided to live there permanently!
What does success mean to you? I would really love to hear that from you guys 🙂